Publications

Learning Neural Generative Dynamics for Molecular Conformation Generation
Minkai Xu
Shitong Luo
Yoshua Bengio
Jian Peng
Jian Tang
We study how to generate molecule conformations (i.e., 3D structures) from a molecular graph. Traditional methods, such as molecular dynamic… (see more)s, sample conformations via computationally expensive simulations. Recently, machine learning methods have shown great potential by training on a large collection of conformation data. Challenges arise from the limited model capacity for capturing complex distributions of conformations and the difficulty in modeling long-range dependencies between atoms. Inspired by the recent progress in deep generative models, in this paper, we propose a novel probabilistic framework to generate valid and diverse conformations given a molecular graph. We propose a method combining the advantages of both flow-based and energy-based models, enjoying: (1) a high model capacity to estimate the multimodal conformation distribution; (2) explicitly capturing the complex long-range dependencies between atoms in the observation space. Extensive experiments demonstrate the superior performance of the proposed method on several benchmarks, including conformation generation and distance modeling tasks, with a significant improvement over existing generative models for molecular conformation sampling.
2020-12-31
ICLR (published)
doi.org
openreview.net
Learning Robust State Abstractions for Hidden-Parameter Block MDPS
Amy Zhang
Shagun Sodhani
Khimya Khetarpal
Joelle Pineau
2020-12-31
ICLR (published)
openreview.net
openreview.net
Learning Task Decomposition with Ordered Memory Policy Network
Yuchen Lu
Yikang Shen
Siyuan Zhou
Aaron Courville
Joshua B. Tenenbaum
Chuang Gan
Many complex real-world tasks are composed of several levels of sub-tasks. Humans leverage these hierarchical structures to accelerate the l… (see more)earning process and achieve better generalization. In this work, we study the inductive bias and propose Ordered Memory Policy Network (OMPN) to discover subtask hierarchy by learning from demonstration. The discovered subtask hierarchy could be used to perform task decomposition, recovering the subtask boundaries in an unstruc-tured demonstration. Experiments on Craft and Dial demonstrate that our modelcan achieve higher task decomposition performance under both unsupervised and weakly supervised settings, comparing with strong baselines. OMPN can also bedirectly applied to partially observable environments and still achieve higher task decomposition performance. Our visualization further confirms that the subtask hierarchy can emerge in our model.
2020-12-31
ICLR (published)
doi.org
openreview.net
Learning a Universal Template for Few-shot Dataset Generalization
Eleni Triantafillou
Hugo Larochelle
Richard Zemel
Vincent Dumoulin
2020-12-31
ICML (published)
proceedings.mlr.press
proceedings.mlr.press
Learning with Gradient Descent and Weakly Convex Losses
Dominic Richards
Michael G. Rabbat
We study the learning performance of gradient descent when the empirical risk is weakly convex, namely, the smallest negative eigenvalue of … (see more)the empirical risk's Hessian is bounded in magnitude. By showing that this eigenvalue can control the stability of gradient descent, generalisation error bounds are proven that hold under a wider range of step sizes compared to previous work. Out of sample guarantees are then achieved by decomposing the test error into generalisation, optimisation and approximation errors, each of which can be bounded and traded off with respect to algorithmic parameters, sample size and magnitude of this eigenvalue. In the case of a two layer neural network, we demonstrate that the empirical risk can satisfy a notion of local weak convexity, specifically, the Hessian's smallest eigenvalue during training can be controlled by the normalisation of the layers, i.e., network scaling. This allows test error guarantees to then be achieved when the population risk minimiser satisfies a complexity assumption. By trading off the network complexity and scaling, insights are gained into the implicit bias of neural network scaling, which are further supported by experimental findings.
2020-12-31
AISTATS (published)
proceedings.mlr.press
proceedings.mlr.press
Machine Learning for Combinatorial Optimization: a Methodological Tour d'Horizon
Yoshua Bengio
Andrea Lodi
Antoine Prouvost
This paper surveys the recent attempts, both from the machine learning and operations research communities, at leveraging machine learning t… (see more)o solve combinatorial optimization problems. Given the hard nature of these problems, state-of-the-art algorithms rely on handcrafted heuristics for making decisions that are otherwise too expensive to compute or mathematically not well defined. Thus, machine learning looks like a natural candidate to make such decisions in a more principled and optimized way. We advocate for pushing further the integration of machine learning and combinatorial optimization and detail a methodology to do so. A main point of the paper is seeing generic optimization problems as data points and inquiring what is the relevant distribution of problems to use for learning on a given task.
2020-12-31
Eur. J. Oper. Res. (published)
doi.org
arxiv.org
MBAIL: Multi-Batch Best Action Imitation Learning utilizing Sample Transfer and Policy Distillation
Dingwei Wu
Tianyu Li
David Meger
M. Jenkin
Steve Liu
Gregory Dudek
Batch reinforcement learning (RL) aims to learn a good control policy from a previously collected dataset without requiring additional inter… (see more)actions with the environment. Unfortunately, in the real world, we may only have a limited amount of training data for tasks we are interested in. Most batch RL methods are intended to learn a policy over one fixed dataset, and are not intended to learn a policy that can perform well over other tasks. How can we leverage the advantages of batch RL while dealing with limited training data is another challenge in real world. In this work, we propose to add sample transfer and policy distillation to a leading Batch RL approach. The proposed methods are evaluated on multiple control tasks to showcase their effectiveness.
2020-12-31
(published)
www.semanticscholar.org
MICo: Improved representations via sampling-based state similarity for Markov decision processes
Pablo Samuel Castro
Tyler Kastner
Prakash Panangaden
Mark Rowland
We present a new behavioural distance over the state space of a Markov decision process, and demonstrate the use of this distance as an effe… (see more)ctive means of shaping the learnt representations of deep reinforcement learning agents. While existing notions of state similarity are typically difficult to learn at scale due to high computational cost and lack of sample-based algorithms, our newly-proposed distance addresses both of these issues. In addition to providing detailed theoretical analyses, we provide empirical evidence that learning this distance alongside the value function yields structured and informative representations, including strong results on the Arcade Learning Environment benchmark.
2020-12-31
Advances in Neural Information Processing Systems 34 (NeurIPS 2021) (published)
openreview.net
openreview.net
MICo: Learning improved representations via sampling-based state similarity for Markov decision processes
Pablo Samuel Castro
Tyler Kastner
Prakash Panangaden
Mark Rowland
We present a new behavioural distance over the state space of a Markov decision process, and demonstrate the use of this distance as an eff… (see more)ective means of shaping the learnt representations of deep reinforcement learning agents. While existing notions of state similarity are typically difficult to learn at scale due to high computational cost and lack of sample-based algorithms, our newly-proposed distance addresses both of these issues. In addition to providing detailed theoretical analysis
2020-12-31
arXiv.org (preprint)
dblp.uni-trier.de
Multi-Agent Estimation and Filtering for Minimizing Team Mean-Squared Error
Mohammad Afshari
Aditya Mahajan
Motivated by estimation problems arising in autonomous vehicles and decentralized control of unmanned aerial vehicles, we consider multi-age… (see more)nt estimation and filtering problems in which multiple agents generate state estimates based on decentralized information and the objective is to minimize a coupled mean-squared error which we call team mean-square error. We call the resulting estimates as minimum team mean-squared error (MTMSE) estimates. We show that MTMSE estimates are different from minimum mean-squared error (MMSE) estimates. We derive closed-form expressions for MTMSE estimates, which are linear function of the observations where the corresponding gain depends on the weight matrix that couples the estimation error. We then consider a filtering problem where a linear stochastic process is monitored by multiple agents which can share their observations (with delay) over a communication graph. We derive expressions to recursively compute the MTMSE estimates. To illustrate the effectiveness of the proposed scheme we consider an example of estimating the distances between vehicles in a platoon and show that MTMSE estimates significantly outperform MMSE estimates and consensus Kalman filtering estimates.
2020-12-31
IEEE Transactions on Signal Processing (published)
doi.org
arxiv.org
2D Multi-Class Model for Gray and White Matter Segmentation of the Cervical Spinal Cord at 7T
Nilser J. Laines Medina
Charley Gros
Julien Cohen-Adad
Virginie Callot
Arnaud Le Troter
The spinal cord (SC), which conveys information between the brain and the peripheral nervous system, plays a key role in various neurologica… (see more)l disorders such as multiple sclerosis (MS) and amyotrophic lateral sclerosis (ALS), in which both gray matter (GM) and white matter (WM) may be impaired. While automated methods for WM/GM segmentation are now largely available, these techniques, developed for conventional systems (3T or lower) do not necessarily perform well on 7T MRI data, which feature finer details, contrasts, but also different artifacts or signal dropout. The primary goal of this study is thus to propose a new deep learning model that allows robust SC/GM multi-class segmentation based on ultra-high resolution 7T T2*-w MR images. The second objective is to highlight the relevance of implementing a specific data augmentation (DA) strategy, in particular to generate a generic model that could be used for multi-center studies at 7T.
2020-12-31
arXiv (preprint)
doi.org
arxiv.org
Multi-Domain Balanced Sampling Improves Out-of-Generalization of Chest X-ray Pathology Prediction Models
Enoch Amoatey Tetteh
Joseph D Viviano
Yoshua Bengio
David M. Krueger
Joseph Paul Cohen
Learning models that generalize under different distribution shifts in medical imaging has been a long-standing research challenge. There ha… (see more)ve been several proposals for efficient and robust visual representation learning among vision research practitioners, especially in the sensitive and critical biomedical domain. In this paper, we propose an idea for out-of-distribution generalization of chest X-ray pathologies that uses a simple balanced batch sampling technique. We observed that balanced sampling between the multiple training datasets improves the performance over baseline models trained without balancing. Code for this work is available on Github. 1
2020-12-31
(published)
www.semanticscholar.org