Search Results for author:
Found 33 papers, 7 papers with code
Unsupervised Translation of Emergent Communication
Emergent Communication (EC) provides a unique window into the language systems that emerge autonomously when agents are trained to jointly achieve shared goals.
Data-dependent and Oracle Bounds on Forgetting in Continual Learning
In continual learning, knowledge must be preserved and re-used between tasks, maintaining good transfer to future tasks and minimizing forgetting of previously learned ones.
Analysis of the Identifying Regulation with Adversarial Surrogates Algorithm
Given a time-series of noisy measured outputs of a dynamical system z[k], k=1... N, the Identifying Regulation with Adversarial Surrogates (IRAS) algorithm aims to find a non-trivial first integral of the system, namely, a scalar function g() such that g(z[i]) = g(z[j]), for all i, j.
Concept-Best-Matching: Evaluating Compositionality in Emergent Communication
Artificial agents that learn to communicate in order to accomplish a given task acquire communication protocols that are typically opaque to a human.
Statistical curriculum learning: An elimination algorithm achieving an oracle risk
In the single source case, we propose an elimination learning method, whose risk matches that of a strong-oracle learner.
Characterization of the Distortion-Perception Tradeoff for Finite Channels with Arbitrary Metrics
We provide a structural characterization of the DP tradeoff, where the DP function is piecewise linear in the perception index.
Identifying Dynamic Regulation with Adversarial Surrogates
Homeostasis, the ability to maintain a stable internal environment in the face of perturbations, is essential for the functioning of living systems.
Emergent Quantized Communication
The field of emergent communication aims to understand the characteristics of communication as it emerges from artificial agents solving tasks that require information exchange.
Integral Probability Metrics PAC-Bayes Bounds
We present a PAC-Bayes-style generalization bound which enables the replacement of the KL-divergence with a variety of Integral Probability Metrics (IPM).
Online Meta-Learning in Adversarial Multi-Armed Bandits
This solution comprises an inner learner that plays each episode separately, and an outer learner that updates the hyper-parameters of the inner algorithm between the episodes.
Enhancing Causal Estimation through Unlabeled Offline Data
Our proposed approach consists of three stages: (i) Use the abundant offline data in order to create both a non-causal and a causal estimator for the relevant unmeasured physiological variables.
Metalearning Linear Bandits by Prior Update
In this work we prove, in the context of stochastic linear bandits and Gaussian priors, that as long as the prior is sufficiently close to the true prior, the performance of the applied algorithm is close to that of the algorithm that uses the true prior.
A Theory of the Distortion-Perception Tradeoff in Wasserstein Space
In this paper, we derive a closed form expression for this distortion-perception (DP) function for the mean squared-error (MSE) distortion and the Wasserstein-2 perception index.
Ensemble Bootstrapping for Q-Learning
Finally, We demonstrate the superior performance of a deep RL variant of EBQL over other deep QL algorithms for a suite of ATARI games.
Discount Factor as a Regularizer in Reinforcement Learning
Specifying a Reinforcement Learning (RL) task involves choosing a suitable planning horizon, which is typically modeled by a discount factor.
Option Discovery in the Absence of Rewards with Manifold Analysis
Options have been shown to be an effective tool in reinforcement learning, facilitating improved exploration and learning.
PAC Guarantees for Cooperative Multi-Agent Reinforcement Learning with Restricted Communication
We develop model free PAC performance guarantees for multiple concurrent MDPs, extending recent works where a single learner interacts with multiple non-interacting agents in a noise free environment.
Multi-agent Reinforcement Learning
reinforcement-learning
+2
Generalization Bounds For Unsupervised and Semi-Supervised Learning With Autoencoders
Autoencoders are widely used for unsupervised learning and as a regularization scheme in semi-supervised learning.
Distributional Multivariate Policy Evaluation and Exploration with the Bellman GAN
In this formulation, DiRL can be seen as learning a deep generative model of the value distribution, driven by the discrepancy between the distribution of the current value, and the distribution of the sum of current reward and next value.
Lifelong Learning by Adjusting Priors
We develop a framework for lifelong learning in deep neural networks that is based on generalization bounds, developed within the PAC-Bayes framework.
Joint autoencoders: a flexible meta-learning framework
Ideally one would like to allow both the data for the current task and for previous related tasks to self-organize the learning system in such a way that commonalities and differences between the tasks are learned in a data-driven fashion.
Meta-Learning by Adjusting Priors Based on Extended PAC-Bayes Theory
In meta-learning an agent extracts knowledge from observed tasks, aiming to facilitate learning of novel future tasks.
Learning an attention model in an artificial visual system
The Human visual perception of the world is of a large fixed image that is highly detailed and sharp.
Optimal Encoding and Decoding for Point Process Observations: an Approximate Closed-Form Filter
The process of dynamic state estimation (filtering) based on point process observations is in general intractable.
A Tractable Approximation to Optimal Point Process Filtering: Application to Neural Encoding
The process of dynamic state estimation (filtering) based on point process observations is in general intractable.
Hierarchical Coupled Geometry Analysis for Neuronal Structure and Activity Pattern Discovery
In the wake of recent advances in experimental methods in neuroscience, the ability to record in-vivo neuronal activity from awake animals has become feasible.
An Analytically Tractable Bayesian Approximation to Optimal Point Process Filtering
The process of dynamic state estimation (filtering) based on point process observations is in general intractable.
Expectation Backpropagation: Parameter-Free Training of Multilayer Neural Networks with Continuous or Discrete Weights
Using online EP and the central limit theorem we find an analytical approximation to the Bayes update of this posterior, as well as the resulting Bayes estimates of the weights and outputs.
Optimal Neural Codes for Control and Estimation
Within the framework of optimal Control Theory, one is usually given a cost function which is minimized by selecting a control law based on the observations.
Optimal Population Codes for Control and Estimation
Within the framework of optimal Control Theory, one is usually given a cost function which is minimized by selecting a control law based on the observations.
Mean Field Bayes Backpropagation: scalable training of multilayer neural networks with binary weights
Significant success has been reported recently using deep neural networks for classification.
Analytical Results for the Error in Filtering of Gaussian Processes
Bayesian filtering of stochastic stimuli has received a great deal of attention re- cently.
Temporal Difference Based Actor Critic Learning - Convergence and Neural Implementation
Actor-critic algorithms for reinforcement learning are achieving renewed popularity due to their good convergence properties in situations where other approaches often fail (e. g., when function approximation is involved).
