Search Results for author: Ron Meir

Found 24 papers, 5 papers with code

Online Meta-Learning in Adversarial Multi-Armed Bandits

no code implementations31 May 2022 Ilya Osadchiy, Kfir Y. Levy, Ron Meir

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.

Meta-Learning Multi-Armed Bandits

Enhancing Causal Estimation through Unlabeled Offline Data

1 code implementation16 Feb 2022 Ron Teichner, Ron Meir, Danny Eitan

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

no code implementations12 Jul 2021 Amit Peleg, Naama Pearl, Ron Meir

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.

Decision Making

A Theory of the Distortion-Perception Tradeoff in Wasserstein Space

no code implementations NeurIPS 2021 Dror Freirich, Tomer Michaeli, Ron Meir

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.

Image Restoration

Ensemble Bootstrapping for Q-Learning

no code implementations28 Feb 2021 Oren Peer, Chen Tessler, Nadav Merlis, Ron Meir

Finally, We demonstrate the superior performance of a deep RL variant of EBQL over other deep QL algorithms for a suite of ATARI games.

Atari Games Q-Learning

Discount Factor as a Regularizer in Reinforcement Learning

1 code implementation ICML 2020 Ron Amit, Ron Meir, Kamil Ciosek

Specifying a Reinforcement Learning (RL) task involves choosing a suitable planning horizon, which is typically modeled by a discount factor.

reinforcement-learning

Option Discovery in the Absence of Rewards with Manifold Analysis

1 code implementation ICML 2020 Amitay Bar, Ronen Talmon, Ron Meir

Options have been shown to be an effective tool in reinforcement learning, facilitating improved exploration and learning.

reinforcement-learning

PAC Guarantees for Cooperative Multi-Agent Reinforcement Learning with Restricted Communication

no code implementations23 May 2019 Or Raveh, Ron Meir

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

Generalization Bounds For Unsupervised and Semi-Supervised Learning With Autoencoders

no code implementations4 Feb 2019 Baruch Epstein, Ron Meir

Autoencoders are widely used for unsupervised learning and as a regularization scheme in semi-supervised learning.

Generalization Bounds

Distributional Multivariate Policy Evaluation and Exploration with the Bellman GAN

no code implementations6 Aug 2018 Dror Freirich, Ron Meir, Aviv Tamar

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.

Joint autoencoders: a flexible meta-learning framework

no code implementations ICLR 2018 Baruch Epstein, Ron Meir, Tomer Michaeli

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.

Domain Adaptation Meta-Learning +1

Lifelong Learning by Adjusting Priors

no code implementations ICLR 2018 Ron Amit, Ron Meir

We develop a framework for lifelong learning in deep neural networks that is based on generalization bounds, developed within the PAC-Bayes framework.

Generalization Bounds

Meta-Learning by Adjusting Priors Based on Extended PAC-Bayes Theory

1 code implementation ICML 2018 Ron Amit, Ron Meir

In meta-learning an agent extracts knowledge from observed tasks, aiming to facilitate learning of novel future tasks.

Meta-Learning

Learning an attention model in an artificial visual system

no code implementations24 Jan 2017 Alon Hazan, Yuval Harel, Ron Meir

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

no code implementations12 Sep 2016 Yuval Harel, Ron Meir, Manfred Opper

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

no code implementations NeurIPS 2015 Yuval Harel, Ron Meir, Manfred Opper

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

no code implementations6 Nov 2015 Gal Mishne, Ronen Talmon, Ron Meir, Jackie Schiller, Uri Dubin, Ronald R. Coifman

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

no code implementations28 Jul 2015 Yuval Harel, Ron Meir, Manfred Opper

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

2 code implementations NeurIPS 2014 Daniel Soudry, Itay Hubara, Ron Meir

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.

Binary text classification Text Classification

Optimal Neural Codes for Control and Estimation

no code implementations NeurIPS 2014 Alex K. Susemihl, Ron Meir, Manfred Opper

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.

Decision Making

Optimal Population Codes for Control and Estimation

no code implementations27 Jun 2014 Alex Susemihl, Ron Meir, Manfred Opper

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.

Temporal Difference Based Actor Critic Learning - Convergence and Neural Implementation

no code implementations NeurIPS 2008 Dotan D. Castro, Dmitry Volkinshtein, Ron Meir

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).

reinforcement-learning

Cannot find the paper you are looking for? You can Submit a new open access paper.