Publications

Check out our people page to get an impression of the research done by the people at AMLab, and of course follow us on Twitter to stay tuned! Below you'll find an archive our groups output in ML research, all the way back to 1994!

2022

1. NeurIPS

   Learning Expressive Meta-Representations with Mixture of Expert Neural Processes

   Wang, Qi, and Hoof, Herke

   In Advances in Neural Information Processing Systems 2022

   Abs

   Neural processes (NPs) formulate exchangeable stochastic processes and are promising models for meta learning that do not require gradient updates during the testing phase. However, most NP variants place a strong emphasis on a global latent variable. This weakens the approximation power and restricts the scope of applications using NP variants, especially when data generative processes are complicated. To resolve these issues, we propose to combine the Mixture of Expert models with Neural Processes to develop more expressive exchangeable stochastic processes, referred to as Mixture of Expert Neural Processes (MoE-NPs). Then we apply MoE-NPs to both few-shot supervised learning and meta reinforcement learning tasks. Empirical results demonstrate MoE-NPs’ strong generalization capability to unseen tasks in these benchmarks.

2. NeurIPS

   Factored Adaptation for Non-Stationary Reinforcement Learning

   Feng, Fan, Huang, Biwei, Zhang, Kun, and Magliacane, Sara

   In Advances in Neural Information Processing Systems 2022

   Abs HTML PDF Code

   Dealing with non-stationarity in environments (e.g., in the transition dynamics) and objectives (e.g., in the reward functions) is a challenging problem that is crucial in real-world applications of reinforcement learning (RL). While most current approaches model the changes as a single shared embedding vector, we leverage insights from the recent causality literature to model non-stationarity in terms of individual latent change factors, and causal graphs across different environments. In particular, we propose Factored Adaptation for Non-Stationary RL (FANS-RL), a factored adaption approach that learns jointly both the causal structure in terms of a factored MDP, and a factored representation of the individual time-varying change factors. We prove that under standard assumptions, we can completely recover the causal graph representing the factored transition and reward function, as well as a partial structure between the individual change factors and the state components. Through our general framework, we can consider general non-stationary scenarios with different function types and changing frequency, including changes across episodes and within episodes. Experimental results demonstrate that FANS-RL outperforms existing approaches in terms of return, compactness of the latent state representation, and robustness to varying degrees of non-stationarity.

3. NeurIPS

   Neural Topological Ordering for Computation Graphs

   Gagrani, Mukul, Rainone, Corrado, Yang, Yang, Teague, Harris, Jeon, Wonseok, Hoof, Herke, Zeng, Weiliang Will, Zappi, Piero, Lott, Christopher, and Bondesan, Roberto

   In Advances in Neural Information Processing Systems 2022

   HTML PDF
4. ICML

   Equivariant diffusion for molecule generation in 3d

   Hoogeboom, Emiel, Satorras, Vı́ctor Garcia, Vignac, Clément, and Welling, Max

   In International Conference on Machine Learning 2022

   Abs HTML PDF Code

   This work introduces a diffusion model for molecule generation in 3D that is equivariant to Euclidean transformations. Our E(3) Equivariant Diffusion Model (EDM) learns to denoise a diffusion process with an equivariant network that jointly operates on both continuous (atom coordinates) and categorical features (atom types). In addition, we provide a probabilistic analysis which admits likelihood computation of molecules using our model. Experimentally, the proposed method significantly outperforms previous 3D molecular generative methods regarding the quality of generated samples and efficiency at training time.

5. ICML

   Lie Point Symmetry Data Augmentation for Neural PDE Solvers

   Brandstetter, Johannes, Welling, Max, and Worrall, Daniel E

   In International Conference on Machine Learning 2022

   Abs HTML PDF Code

   Neural networks are increasingly being used to solve partial differential equations (PDEs), replacing slower numerical solvers. However, a critical issue is that neural PDE solvers require high-quality ground truth data, which usually must come from the very solvers they are designed to replace. Thus, we are presented with a proverbial chicken-and-egg problem. In this paper, we present a method, which can partially alleviate this problem, by improving neural PDE solver sample complexity – Lie point symmetry data augmentation (LPSDA). In the context of PDEs, it turns out that we are able to quantitatively derive an exhaustive list of data transformations, based on the Lie point symmetry group of the PDEs in question, something not possible in other application areas. We present this framework and demonstrate how it can easily be deployed to improve neural PDE solver sample complexity by an order of magnitude.

6. ICML

   Exploiting Redundancy: Separable Group Convolutional Networks on Lie Groups

   Knigge, David M, Romero, David W, and Bekkers, Erik J

   International Conference on Machine Learning 2022

   Abs HTML PDF Code

   Group convolutional neural networks (G-CNNs) have been shown to increase parameter efficiency and model accuracy by incorporating geometric inductive biases. In this work, we investigate the properties of representations learned by regular G-CNNs, and show considerable parameter redundancy in group convolution kernels. This finding motivates further weight-tying by sharing convolution kernels over subgroups. To this end, we introduce convolution kernels that are separable over the subgroup and channel dimensions. In order to obtain equivariance to arbitrary affine Lie groups we provide a continuous parameterisation of separable convolution kernels. We evaluate our approach across several vision datasets, and show that our weight sharing leads to improved performance and computational efficiency. In many settings, separable G-CNNs outperform their non-separable counterpart, while only using a fraction of their training time. In addition, thanks to the increase in computational efficiency, we are able to implement G-CNNs equivariant to the Sim(2) group; the group of dilations, rotations and translations. Sim(2)-equivariance further improves performance on all tasks considered.

7. ICML

   CITRIS: Causal Identifiability from Temporal Intervened Sequences

   Lippe, Phillip, Magliacane, Sara, Löwe, Sindy, Asano, Yuki M, Cohen, Taco, and Gavves, Efstratios

   International Conference on Machine Learning 2022

   Abs HTML PDF Code

   Understanding the latent causal factors of a dynamical system from visual observations is a crucial step towards agents reasoning in complex environments. In this paper, we propose CITRIS, a variational autoencoder framework that learns causal representations from temporal sequences of images in which underlying causal factors have possibly been intervened upon. In contrast to the recent literature, CITRIS exploits temporality and observing intervention targets to identify scalar and multidimensional causal factors, such as 3D rotation angles. Furthermore, by introducing a normalizing flow, CITRIS can be easily extended to leverage and disentangle representations obtained by already pretrained autoencoders. Extending previous results on scalar causal factors, we prove identifiability in a more general setting, in which only some components of a causal factor are affected by interventions. In experiments on 3D rendered image sequences, CITRIS outperforms previous methods on recovering the underlying causal variables. Moreover, using pretrained autoencoders, CITRIS can even generalize to unseen instantiations of causal factors, opening future research areas in sim-to-real generalization for causal representation learning.

8. ICML

   Learning Symmetric Embeddings for Equivariant World Models

   Park, Jung Yeon, Biza, Ondrej, Zhao, Linfeng, Meent, Jan-Willem, and Walters, Robin

   In International Conference on Machine Learning 2022

   Abs PDF

   Incorporating symmetries can lead to highly data-efficient and generalizable models by defining equivalence classes of data samples related by transformations. However, characterizing how transformations act on input data is often difficult, limiting the applicability of equivariant models. We propose learning symmetric embedding networks (SENs) that encode an input space (e.g. images), where we do not know the effect of transformations (e.g. rotations), to a feature space that transforms in a known manner under these operations. This network can be trained end-to-end with an equivariant task network to learn an explicitly symmetric representation. We validate this approach in the context of equivariant transition models with 3 distinct forms of symmetry. Our experiments demonstrate that SENs facilitate the application of equivariant networks to data with complex symmetry representations. Moreover, doing so can yield improvements in accuracy and generalization relative to both fully-equivariant and non-equivariant baselines.

9. ICML

   Adapting the Linearised Laplace Model Evidence for Modern Deep Learning

   Antoran, Javier, Janz, David, Allingham, James Urquhart, Daxberger, Erik, Barbano, Riccardo, Nalisnick, Eric, and Hernandez-Lobato, Jose Miguel

   In Proceedings of the 39th International Conference on Machine Learning 2022

   Abs HTML PDF

   The linearised Laplace method for estimating model uncertainty has received renewed attention in the Bayesian deep learning community. The method provides reliable error bars and admits a closed-form expression for the model evidence, allowing for scalable selection of model hyperparameters. In this work, we examine the assumptions behind this method, particularly in conjunction with model selection. We show that these interact poorly with some now-standard tools of deep learning–stochastic approximation methods and normalisation layers–and make recommendations for how to better adapt this classic method to the modern setting. We provide theoretical support for our recommendations and validate them empirically on MLPs, classic CNNs, residual networks with and without normalisation layers, generative autoencoders and transformers.

10. ICML

    Calibrated Learning to Defer with One-vs-All Classifiers

    Verma, Rajeev, and Nalisnick, Eric

    In Proceedings of the 39th International Conference on Machine Learning 2022

    Abs HTML PDF

    The learning to defer (L2D) framework has the potential to make AI systems safer. For a given input, the system can defer the decision to a human if the human is more likely than the model to take the correct action. We study the calibration of L2D systems, investigating if the probabilities they output are sound. We find that Mozannar & Sontag’s (2020) multiclass framework is not calibrated with respect to expert correctness. Moreover, it is not even guaranteed to produce valid probabilities due to its parameterization being degenerate for this purpose. We propose an L2D system based on one-vs-all classifiers that is able to produce calibrated probabilities of expert correctness. Furthermore, our loss function is also a consistent surrogate for multiclass L2D, like Mozannar & Sontag’s (2020). Our experiments verify that not only is our system calibrated, but this benefit comes at no cost to accuracy. Our model’s accuracy is always comparable (and often superior) to Mozannar & Sontag’s (2020) model’s in tasks ranging from hate speech detection to galaxy classification to diagnosis of skin lesions.

11. ICML

    Model-based Meta Reinforcement Learning using Graph Structured Surrogate Models and Amortized Policy Search

    Wang, Q., and Hoof, H.

    In International Conference on Machine Learning 2022

    Abs PDF

    Reinforcement learning is a promising paradigm for solving sequential decision-making problems, but low data efficiency and weak generalization across tasks are bottlenecks in real-world applications. Model-based meta reinforcement learning addresses these issues by learning dynamics and leveraging knowledge from prior experience. In this paper, we take a closer look at this framework and propose a new posterior sampling based approach that consists of a new model to identify task dynamics together with an amortized policy optimization step. We show that our model, called a graph structured surrogate model (GSSM), achieves competitive dynamics prediction performance with lower model complexity. Moreover, our approach in policy search is able to obtain high returns and allows fast execution by avoiding test-time policy gradient updates.

12. MIDL

    Experimental design for MRI by greedy policy search

    Bakker, T., Muckley, M., Romero-Soriano, A., Drozdzal, M., and Pineda, L.

    In Proceedings of Machine Learning Research Jul 2022

    PDF Code
13. CLeaR

    Amortized Causal Discovery: Learning to Infer Causal Graphs from Time-Series Data

    Löwe, S., Madras, D., Zemel, R., and Welling, M.

    Causal Learning and Reasoning Jul 2022

    Abs HTML PDF Code

    On time-series data, most causal discovery methods fit a new model whenever they encounter samples from a new underlying causal graph. However, these samples often share relevant information which is lost when following this approach. Specifically, different samples may share the dynamics which describe the effects of their causal relations. We propose Amortized Causal Discovery, a novel framework that leverages such shared dynamics to learn to infer causal relations from time-series data. This enables us to train a single, amortized model that infers causal relations across samples with different underlying causal graphs, and thus leverages the shared dynamics information. We demonstrate experimentally that this approach, implemented as a variational model, leads to significant improvements in causal discovery performance, and show how it can be extended to perform well under added noise and hidden confounding.

14. ICLR

    Geometric and Physical Quantities improve E (3) Equivariant Message Passing

    Brandstetter, Johannes, Hesselink, Rob, Pol, Elise, Bekkers, Erik, and Welling, Max

    In International Conference on Learning Representations Jul 2022

    Abs HTML PDF Code

    Including covariant information, such as position, force, velocity or spin is important in many tasks in computational physics and chemistry. We introduce Steerable E(3) Equivariant Graph Neural Networks (SEGNNs) that generalise equivariant graph networks, such that node and edge attributes are not restricted to invariant scalars, but can contain covariant information, such as vectors or tensors. This model, composed of steerable MLPs, is able to incorporate geometric and physical information in both the message and update functions. Through the definition of steerable node attributes, the MLPs provide a new class of activation functions for general use with steerable feature fields. We discuss ours and related work through the lens of equivariant non-linear convolutions, which further allows us to pin-point the successful components of SEGNNs: non-linear message aggregation improves upon classic linear (steerable) point convolutions; steerable messages improve upon recent equivariant graph networks that send invariant messages. We demonstrate the effectiveness of our method on several tasks in computational physics and chemistry and provide extensive ablation studies.

15. ICLR

    Self-Supervised Inference in State-Space Models

    Ruhe, David, and Forré, Patrick

    In International Conference on Learning Representations Jul 2022

    Abs HTML PDF

    We perform approximate inference in state-space models with nonlinear state transitions. Without parameterizing a generative model, we apply Bayesian update formulas using a local linearity approximation parameterized by neural networks. It comes accompanied by a maximum likelihood objective that requires no supervision via uncorrupt observations or ground truth latent states. The optimization backpropagates through a recursion similar to the classical Kalman filter and smoother. Additionally, using an approximate conditional independence, we can perform smoothing without having to parameterize a separate model. In scientific applications, domain knowledge can give a linear approximation of the latent transition maps, which we can easily incorporate into our model. Usage of such domain knowledge is reflected in excellent results (despite our model’s simplicity) on the chaotic Lorenz system compared to fully supervised and variational inference methods. Finally, we show competitive results on an audio denoising experiment.

16. ASCOM

    Detecting dispersed radio transients in real time using convolutional neural networks

    Ruhe, David, Kuiack, Mark, Rowlinson, Antonia, Wijers, Ralph, and Forré, Patrick

    Astronomy and Computing Jul 2022

    HTML PDF
17. ICLR

    Multi-Agent MDP Homomorphic Networks

    Pol, Elise, Hoof, Herke, Oliehoek, Frans, and Welling, Max

    In International Conference on Learning Representations Jul 2022

    Abs HTML PDF

    This paper introduces Multi-Agent MDP Homomorphic Networks, a class of networks that allows distributed execution using only local information, yet is able to share experience between global symmetries in the joint state-action space of cooperative multi-agent systems. In cooperative multi-agent systems, complex symmetries arise between different configurations of the agents and their local observations. For example, consider a group of agents navigating: rotating the state globally results in a permutation of the optimal joint policy. Existing work on symmetries in single agent reinforcement learning can only be generalized to the fully centralized setting, because such approaches rely on the global symmetry in the full state-action spaces, and these can result in correspondences across agents. To encode such symmetries while still allowing distributed execution we propose a factorization that decomposes global symmetries into local transformations. Our proposed factorization allows for distributing the computation that enforces global symmetries over local agents and local interactions. We introduce a multi-agent equivariant policy network based on this factorization. We show empirically on symmetric multi-agent problems that globally symmetric distributable policies improve data efficiency compared to non-equivariant baselines.

18. CPAIOR

    Deep Policy Dynamic Programming for Vehicle Routing Problems

    Kool, Wouter, Hoof, Herke, Gromicho, Joaquim, and Welling, Max

    In International Conference on the Integration of Constraint Programming, Artificial Intelligence, and Operations Research Jul 2022

    PDF Code
19. AAAI

    Fast and Data Efficient Reinforcement Learning from Pixels via Non-Parametric Value Approximation

    Long, Alex, Blair, Alan, and Hoof, Herke

    In AAAI National Conference on Artificial Intelligence Jul 2022

    HTML PDF
20. IJCAI

    Value Refinement Network (VRN)

    Wöhlke, Jan, Schmitt, Felix, and Hoof, Herke

    In International Joint Conference on Artificial Intelligence Jul 2022

    HTML
21. IJCAI

    Leveraging class abstraction for commonsense reinforcement learning via residual policy gradient methods

    Höpner, Niklas, Tiddi, Ilaria, and Hoof, Herke

    In International Joint Conference on Artificial Intelligence Jul 2022

    HTML PDF

2021

1. NeurIPS

   Modeling Category-Selective Cortical Regions with Topographic Variational Autoencoders

   Keller, T. Anderson, Gao, Qinghe, and Welling, Max

   In SVRHM 2021 Workshop at NeurIPS 2021

   Abs PDF

   Category-selectivity in the brain describes the observation that certain spatially localized areas of the cerebral cortex tend to respond robustly and selectively to stimuli from specific limited categories. One of the most well known examples of category-selectivity is the Fusiform Face Area (FFA), an area of the inferior temporal cortex in primates which responds preferentially to images of faces when compared with objects or other generic stimuli. In this work, we leverage the newly introduced Topographic Variational Autoencoder to model the emergence of such localized category-selectivity in an unsupervised manner. Experimentally, we demonstrate our model yields spatially dense neural clusters selective to faces, bodies, and places through visualized maps of Cohen’s d metric. We compare our model with related supervised approaches, namely the Topographic Deep Artificial Neural Network (TDANN) of Lee et al., and discuss both theoretical and empirical similarities. Finally, we show preliminary results suggesting that our model yields a nested spatial hierarchy of increasingly abstract categories, analogous to observations from the human ventral temporal cortex.

2. ICCV

   Predictive Coding With Topographic Variational Autoencoders

   Keller, T. Anderson, and Welling, Max

   In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops Oct 2021

   Abs PDF

   Category-selectivity in the brain describes the observation that certain spatially localized areas of the cerebral cortex tend to respond robustly and selectively to stimuli from specific limited categories. One of the most well known examples of category-selectivity is the Fusiform Face Area (FFA), an area of the inferior temporal cortex in primates which responds preferentially to images of faces when compared with objects or other generic stimuli. In this work, we leverage the newly introduced Topographic Variational Autoencoder to model of the emergence of such localized category-selectivity in an unsupervised manner. Experimentally, we demonstrate our model yields spatially dense neural clusters selective to faces, bodies, and places through visualized maps of Cohen’s d metric. We compare our model with related supervised approaches, namely the TDANN, and discuss both theoretical and empirical similarities. Finally, we show preliminary results suggesting that our model yields a nested spatial hierarchy of increasingly abstract categories, analogous to observations from the human ventral temporal cortex.

3. NeurIPS

   Topographic VAEs learn Equivariant Capsules

   Keller, T. Anderson, and Welling, Max

   In Advances in Neural Information Processing Systems Oct 2021

   Abs PDF

   In this work we seek to bridge the concepts of topographic organization and equivariance in neural networks. To accomplish this, we introduce the Topographic VAE: a novel method for efficiently training deep generative models with topographically organized latent variables. We show that such a model indeed learns to organize its activations according to salient characteristics such as digit class, width, and style on MNIST. Furthermore, through topographic organization over time (i.e. temporal coherence), we demonstrate how predefined latent space transformation operators can be encouraged for observed transformed input sequences – a primitive form of unsupervised learned equivariance. We demonstrate that this model successfully learns sets of approximately equivariant features (i.e. "capsules") directly from sequences and achieves higher likelihood on correspondingly transforming test sequences. Equivariance is verified quantitatively by measuring the approximate commutativity of the inference network and the sequence transformations. Finally, we demonstrate approximate equivariance to complex transformations, expanding upon the capabilities of existing group equivariant neural networks.

4. ICML

   Self Normalizing Flows

   Keller, T. Anderson, Peters, Jorn W.T., Jaini, Priyank, Hoogeboom, Emiel, Forré, Patrick, and Welling, Max

   In Proceedings of the 38th International Conference on Machine Learning 18–24 jul 2021

   Abs PDF

   Efficient gradient computation of the Jacobian determinant term is a core problem in many machine learning settings, and especially so in the normalizing flow framework. Most proposed flow models therefore either restrict to a function class with easy evaluation of the Jacobian determinant, or an efficient estimator thereof. However, these restrictions limit the performance of such density models, frequently requiring significant depth to reach desired performance levels. In this work, we propose \emphSelf Normalizing Flows, a flexible framework for training normalizing flows by replacing expensive terms in the gradient by learned approximate inverses at each layer. This reduces the computational complexity of each layer’s exact update from \mathcalO(D^3) to \mathcalO(D^2), allowing for the training of flow architectures which were otherwise computationally infeasible, while also providing efficient sampling. We show experimentally that such models are remarkably stable and optimize to similar data likelihood values as their exact gradient counterparts, while training more quickly and surpassing the performance of functionally constrained counterparts.

5. NeurIPS

   As easy as APC: Leveraging self-supervised learning in the context of time series classification with varying levels of sparsity and severe class imbalance

   Wever, Fiorella, Keller, T. Anderson, Garcia, Victor, and Symul, Laura

   In Self-Supervised Learning Workshop at NeurIPS 18–24 jul 2021

   Abs PDF

   High levels of missing data and strong class imbalance are ubiquitous challenges that are often presented simultaneously in real-world time series data. Existing methods approach these problems separately, frequently making significant assumptions about the underlying data generation process in order to lessen the impact of missing information. In this work, we instead demonstrate how a general self-supervised training method, namely Autoregressive Predictive Coding (APC), can be leveraged to overcome both missing data and class imbalance simultaneously without strong assumptions. Specifically, on a synthetic dataset, we show that standard baselines are substantially improved upon through the use of APC, yielding the greatest gains in the combined setting of high missingness and severe class imbalance. We further apply APC on two real-world medical time-series datasets, and show that APC improves the classification performance in all settings, ultimately achieving state-of-the-art AUPRC results on the Physionet benchmark

6. UAI

   Variational combinatorial sequential Monte Carlo methods for Bayesian phylogenetic inference

   Moretti, Antonio Khalil, Zhang, Liyi, Naesseth, Christian A., Venner, Hadiah, Blei, David, and Pe’er, Itsik

   In Proceedings of the Thirty-Seventh Conference on Uncertainty in Artificial Intelligence 27–30 jul 2021

   PDF
7. AISTATS

   Rate-Regularization and Generalization in Variational Autoencoders

   Bozkurt, Alican, Esmaeili, Babak, Tristan, Jean-Baptiste, Brooks, Dana, Dy, Jennifer, and Meent, Jan-Willem

   In International Conference on Artificial Intelligence and Statistics Mar 2021

   Abs HTML PDF

   Variational autoencoders (VAEs) optimize an objective that comprises a reconstruction loss (the distortion) and a KL term (the rate). The rate is an upper bound on the mutual information, which is...

8. NeurIPS

   Nested Variational Inference

   Zimmermann, Heiko, Wu, Hao, Esmaeili, Babak, and Meent, Jan-Willem

   In Advances in Neural Information Processing Systems Mar 2021

   HTML PDF
9. ICML

   Conjugate Energy-Based Models

   Wu, Hao*, Esmaeili, Babak*, Wick, Michael, Tristan, Jean-Baptiste, and van de Meent, Jan-Willem

   In Proceedings of the 38th International Conference on Machine Learning (ICML) 18–24 jul 2021

   Abs HTML PDF

   In this paper, we propose conjugate energy-based models (CEBMs), a new class of energy-based models that define a joint density over data and latent variables. The joint density of a CEBM decomposes into an intractable distribution over data and a tractable posterior over latent variables. CEBMs have similar use cases as variational autoencoders, in the sense that they learn an unsupervised mapping from data to latent variables. However, these models omit a generator network, which allows them to learn more flexible notions of similarity between data points. Our experiments demonstrate that conjugate EBMs achieve competitive results in terms of image modelling, predictive power of latent space, and out-of-domain detection on a variety of datasets.

10. UAI

    Learning proposals for probabilistic programs with inference combinators

    Stites, Sam, Zimmermann, Heiko, Wu, Hao, Sennesh, Eli, and Meent, Jan-Willem

    In Proceedings of the Thirty-Seventh Conference on Uncertainty in Artificial Intelligence 27–30 jul 2021

    Abs HTML PDF Code

    We develop operators for construction of proposals in probabilistic programs, which we refer to as inference combinators. Inference combinators define a grammar over importance samplers that compose primitive operations such as application of a transition kernel and importance resampling. Proposals in these samplers can be parameterized using neural networks, which in turn can be trained by optimizing variational objectives. The result is a framework for user-programmable variational methods that are correct by construction and can be tailored to specific models. We demonstrate the flexibility of this framework by implementing advanced variational methods based on amortized Gibbs sampling and annealing.

11. AISTATS

    Predictive Complexity Priors

    Nalisnick, Eric, Gordon, Jonathan, and Miguel Hernandez-Lobato, Jose

    In Proceedings of The 24th International Conference on Artificial Intelligence and Statistics 13–15 apr 2021

    HTML PDF
12. ICML

    Bayesian Deep Learning via Subnetwork Inference

    Daxberger, Erik, Nalisnick, Eric, Allingham, James U, Antoran, Javier, and Hernandez-Lobato, Jose Miguel

    In Proceedings of the 38th International Conference on Machine Learning 18–24 jul 2021

    PDF
13. JMLR

    Normalizing Flows for Probabilistic Modeling and Inference

    Papamakarios, George, Nalisnick, Eric, Rezende, Danilo Jimenez, Mohamed, Shakir, and Lakshminarayanan, Balaji

    Journal of Machine Learning Research 18–24 jul 2021

    PDF
14. JMS

    Optimizing Adaptive Notifications in Mobile Health Interventions Systems: Reinforcement Learning from a Data-driven Behavioral Simulator

    Wang, Shihan, Zhang, Chao, Kröse, Ben, and Hoof, Herke

    Journal of Medical Systems 18–24 jul 2021

    HTML
15. IJERPH

    Reinforcement Learning to Send Reminders at Right Moments in Smartphone Exercise Application: A Feasibility Study

    Wang, S., Sporrel, K., Hoof, H., Simons, M., Boer, R., Ettema, D., Nibbeling, N., Deutekom, M., and Kröse, B.

    International Journal of Environmental Research and Public Health, Special Issue 18–24 jul 2021

    HTML PDF
16. ICRA

    Hierarchies of Planning and Reinforcement Learning for Robot Navigation

    Wöhlke, J., Schmitt, F., and Hoof, H.

    In IEEE International Conference on Robotics and Automation 18–24 jul 2021

    HTML PDF Code
17. ICML

    Deep Coherent Exploration For Continuous Control

    Zhang, Yijie, and Hoof, Herke

    In International Conference on Machine Learning 18–24 jul 2021

    HTML PDF
18. UrbComp

    Back to Basics: Deep Reinforcement Learning in Traffic Signal Control

    Kanis, S., Samson, L., Bloembergen, D., and Bakker, T.

    The 10th International Workshop on Urban Computing Nov 2021

    PDF Code

All Publications (via Pure)