• Publications
  • Influence
Improving the Robustness of Deep Neural Networks via Stability Training
In this paper we address the issue of output instability of deep neural networks: small perturbations in the visual input can significantly distort the feature embeddings and output of a neuralExpand
  • 271
  • 17
  • PDF
Long-term Forecasting using Tensor-Train RNNs
We present Tensor-Train RNN (TT-RNN), a novel family of neural sequence architectures for multivariate forecasting in environments with nonlinear dynamics. Long-term forecasting in such systems isExpand
  • 60
  • 7
  • PDF
NAOMI: Non-Autoregressive Multiresolution Sequence Imputation
Missing value imputation is a fundamental problem in spatiotemporal modeling, from motion tracking to the dynamics of physical systems. Deep autoregressive models suffer from error propagation whichExpand
  • 12
  • 4
  • PDF
Generating Long-term Trajectories Using Deep Hierarchical Networks
We study the problem of modeling spatiotemporal trajectories over long time horizons using expert demonstrations. For instance, in sports, agents often choose action sequences with long-term goals inExpand
  • 56
  • 3
  • PDF
Generating Multi-Agent Trajectories using Programmatic Weak Supervision
We study the problem of training sequential generative models for capturing coordinated multi-agent trajectory behavior, such as offensive basketball gameplay. When modeling such settings, it isExpand
  • 20
  • 2
  • PDF
On the Generalization Gap in Reparameterizable Reinforcement Learning
Understanding generalization in reinforcement learning (RL) is a significant challenge, as many common assumptions of traditional supervised learning theory do not apply. We focus on the specialExpand
  • 6
  • 2
  • PDF
Generative Multi-Agent Behavioral Cloning
We propose and study the problem of generative multi-agent behavioral cloning, where the goal is to learn a generative, i.e., non-deterministic, multi-agent policy from pre-collected demonstrationExpand
  • 18
  • 1
  • PDF
Novel deep learning methods for track reconstruction
For the past year, the HEP.TrkX project has been investigating machine learning solutions to LHC particle track reconstruction problems. A variety of models were studied that drew inspiration fromExpand
  • 27
  • 1
  • PDF
The HEP.TrkX Project: deep neural networks for HL-LHC online and offline tracking
Particle track reconstruction in dense environments such as the detectors of the High Luminosity Large Hadron Collider (HL-LHC) is a challenging pattern recognition problem. Traditional trackingExpand
  • 21
  • 1
  • PDF
Keeping Your Distance: Solving Sparse Reward Tasks Using Self-Balancing Shaped Rewards
While using shaped rewards can be beneficial when solving sparse reward tasks, their successful application often requires careful engineering and is problem specific. For instance, in tasks whereExpand
  • 6
  • 1
  • PDF