research
∙
09/29/2022
Does Zero-Shot Reinforcement Learning Exist?
A zero-shot RL agent is an agent that can solve any RL task in a given e...
share
research
∙
05/30/2022
Agnostic Physics-Driven Deep Learning
This work establishes that a physical system can perform statistical lea...
research
∙
06/16/2021
Unbiased Methods for Multi-Goal Reinforcement Learning
In multi-goal reinforcement learning (RL) settings, the reward for each ...
research
∙
03/14/2021
Learning One Representation to Optimize All Rewards
We introduce the forward-backward (FB) representation of the dynamics of...
research
∙
01/18/2021
Learning Successor States and Goal-Dependent Values: A Mathematical Viewpoint
In reinforcement learning, temporal difference-based algorithms can be s...
research
∙
05/12/2020
Convergence of Online Adaptive and Recurrent Optimization Algorithms
We prove local convergence of several notable gradient descentalgorithms...
research
∙
02/01/2020
Interpreting a Penalty as the Influence of a Bayesian Prior
In machine learning, it is common to optimize the parameters of a probab...
research
∙
08/29/2019
White-box vs Black-box: Bayes Optimal Strategies for Membership Inference
Membership inference determines, given a sample and trained parameters o...
research
∙
02/05/2019
Separating value functions across time-scales
In many finite horizon episodic reinforcement learning (RL) settings, it...
research
∙
01/28/2019
Making Deep Q-learning methods robust to time discretization
Despite remarkable successes, Deep Reinforcement Learning (DRL) is not r...
research
∙
01/03/2019
The Extended Kalman Filter is a Natural Gradient Descent in Trajectory Space
The extended Kalman filter is perhaps the most standard tool to estimate...
research
∙
10/02/2018
Learning with Random Learning Rates
Hyperparameter tuning is a bothersome step in the training of deep learn...
research
∙
06/19/2018
Mixed batches and symmetric discriminators for GAN training
Generative adversarial networks (GANs) are pow- erful generative models ...
research
∙
05/02/2018
Approximate Temporal Difference Learning is a Gradient Descent for Reversible Policies
In reinforcement learning, temporal difference (TD) is the most direct a...
research
∙
03/23/2018
Can recurrent neural networks warp time?
Successful recurrent models such as long short-term memories (LSTMs) and...
research
∙
02/20/2018
Do Deep Learning Models Have Too Many Parameters? An Information Theory Viewpoint
Deep learning models often have more parameters than observations, and s...
research
∙
02/05/2018
Adversarial Vulnerability of Neural Networks Increases With Input Dimension
Over the past four years, neural networks have proven vulnerable to adve...
research
∙
12/22/2017
True Asymptotic Natural Gradient Optimization
We introduce a simple algorithm, True Asymptotic Natural Gradient Optimi...
research
∙
12/04/2017
Natural Langevin Dynamics for Neural Networks
One way to avoid overfitting in machine learning is to use model paramet...
research
∙
05/23/2017
Unbiasing Truncated Backpropagation Through Time
Truncated Backpropagation Through Time (truncated BPTT) is a widespread ...
research
∙
03/01/2017
Online Natural Gradient as a Kalman Filter
We establish a full relationship between Kalman filtering and Amari's na...
research
∙
02/16/2017
Unbiased Online Recurrent Optimization
The novel Unbiased Online Recurrent Optimization (UORO) algorithm allows...
research
∙
02/25/2016
Practical Riemannian Neural Networks
We provide the first experimental results on non-synthetic datasets for ...
research
∙
11/08/2015
Speed learning on the fly
The practical performance of online stochastic gradient descent algorith...
research
∙
07/28/2015
Training recurrent networks online without backtracking
We introduce the "NoBackTrack" algorithm to train the parameters of dyna...
research
∙
03/30/2014
Auto-encoders: reconstruction versus compression
We discuss the similarities and differences between training an auto-enc...
research
∙
06/03/2013
Riemannian metrics for neural networks II: recurrent networks and learning symbolic data sequences
Recurrent neural networks are powerful models for sequential data, able ...
research
∙
03/04/2013
Riemannian metrics for neural networks I: feedforward networks
We describe four algorithms for neural network training, each adapted to...
research
∙
12/07/2012
Layer-wise learning of deep generative models
When using deep, multi-layered architectures to build generative models ...
research
∙
11/16/2012