You are all cordially invited to the AMLab seminar on Thursday Feb 28th at 16:00 in C3.163, where Christos Louizos will give a talk titled “Learning Exchangeable Distributions”. Afterwards there are the usual drinks and snacks!
Abstract: We present a new family of models that directly parametrize exchangeable distributions; it is realized via the introduction of an explicit model for the dependency structure of the joint probability distribution over the data, while respecting the permutation invariance of an exchangeable distribution. This is achieved by combining two recent advances in variational inference and probabilistic modelling for graphs, normalizing flows and (di)graphons. We, empirically, demonstrate that such models are also approximately consistent, hence they can also provide epistemic uncertainty about their predictions without positing an explicit prior over global variables. We show how to train such models on data and evaluate their predictive capabilities as well as the quality of their uncertainty on various tasks.
You are all cordially invited to the AMLab seminar on Thursday Feb 21st at 16:00 in C3.163, where Thomas Kipf will give a talk titled “Compositional Imitation Learning: Explaining and executing one task at a time”. Afterwards there are the usual drinks and snacks!
Abstract: We introduce a framework for Compositional Imitation Learning and Execution (CompILE) of hierarchically-structured behavior. CompILE learns reusable, variable-length segments of behavior from demonstration data using a novel unsupervised, fully-differentiable sequence segmentation module. These learned behaviors can then be re-composed and executed to perform new tasks. At training time, CompILE auto-encodes observed behavior into a sequence of latent codes, each corresponding to a variable-length segment in the input sequence. Once trained, our model generalizes to sequences of longer length and from environment instances not seen during training. We evaluate our model in a challenging 2D multi-task environment and show that CompILE can find correct task boundaries and event encodings in an unsupervised manner without requiring annotated demonstration data. Latent codes and associated behavior policies discovered by CompILE can be used by a hierarchical agent, where the high-level policy selects actions in the latent code space, and the low-level, task-specific policies are simply the learned decoders. We found that our agent could learn given only sparse rewards, where agents without task-specific policies struggle.
You are all cordially invited to the AMLab seminar on Thursday 14th Feb at 16:00 in C3.163, where Victor Garcia will give a talk titled “GRIN: Graphical Recurrent Inference Networks“. Afterwards there are the usual drinks and snacks!
Abstract: A graphical model is a structured representation of the data generating process. The traditional method to reason over random variables is to perform inference in this graphical model. However, in many cases the generating process is only a poor approximation of the much more complex true data generation process, leading to poor posterior estimates. The subtleties of the generative process are however captured in the data itself and we can “learn to infer”, that is, learn a direct mapping from observations to explanatory latent variables. In this work we propose a hybrid model that combines graphical inference with a learned inverse model, which we structure as a graph neural network. The iterative algorithm is formulated as a recurrent neural network. By using cross-validation we can automatically balance the amount of work performed by graphical inference versus learned inference. We apply our ideas to the Kalman filter, a Gaussian hidden Markov model for time sequences. We apply our “Graphical Recurrent Inference” method to a number of path estimation tasks and show that it successfully outperforms either learned or graphical inference run in isolation.
You are all cordially invited to the AMLab seminar on Thursday January 31 at 16:00 in C3.163, where Emiel Hoogeboom will give a talk titled “Emerging Convolutions for Generative Normalizing Flows”. Afterwards there are the usual drinks and snacks!
Abstract: Generative flows are attractive because they admit exact likelihood optimization and efficient image synthesis. Recently, Kingma & Dhariwal (2018) demonstrated with Glow that generative flows are capable of generating high quality images. We generalize the 1 x 1 convolutions proposed in Glow to invertible d x d convolutions, which are more flexible since they operate on both channel and spatial axes. We propose two methods to produce invertible convolutions that have receptive fields identical to standard convolutions: Emerging convolutions are obtained by chaining specific autoregressive convolutions, and periodic convolutions are decoupled in the frequency domain. Our experiments show that the flexibility of d x d convolutions significantly improves the performance of generative flow models on galaxy images, CIFAR10 and ImageNet.
You are all cordially invited to the AMLab seminar on Thursday January 17 at 16:00 in C3.163, where Herke van Hoof will give a talk titled “Learning Selective Coverage Strategies for Surveying and Search”. Afterwards there are the usual drinks and snacks!
Abstract: In this seminar, I’ll present a project I’ve been working on with Sandeep Manjanna and Gregory Dudek (Mobile Robotics Lab, McGill University). In this project, we investigated selective coverage strategies for a robot tasked with surveying or searching prioritised locations in a given area. This problem can be modelled as a Markov decision process and solved with reinforcement learning strategies, but the state space is extremely large, requiring these states to be aggregated. The proposed state aggregation method is shown to generalize well between different environments. In field tests over reefs at the Folkestone Marine Reserve, using this method an autonomous surface vehicle was able to improve the number of useable visual data samples.