Zobrazeno 1 - 10
of 136
pro vyhledávání: '"Weinberger, Nir"'
Motivated by communication systems with constrained complexity, we consider the problem of input symbol selection for discrete memoryless channels (DMCs). Given a DMC, the goal is to find a subset of its input alphabet, so that the optimal input dist
Externí odkaz:
http://arxiv.org/abs/2407.01263
Autor:
Merhav, Neri, Weinberger, Nir
This monograph offers a toolbox of mathematical techniques, which have been effective and widely applicable in information-theoretic analysis. The first tool is a generalization of the method of types to Gaussian settings, and then to general exponen
Externí odkaz:
http://arxiv.org/abs/2406.00744
In many sequential decision problems, an agent performs a repeated task. He then suffers regret and obtains information that he may use in the following rounds. However, sometimes the agent may also obtain information and avoid suffering regret by qu
Externí odkaz:
http://arxiv.org/abs/2405.16581
We consider a molecular channel, in which messages are encoded to the frequency of objects (or concentration of molecules) in a pool, and whose output during reading time is a noisy version of the input frequencies, as obtained by sampling with repla
Externí odkaz:
http://arxiv.org/abs/2405.07785
Autor:
Rameshwar, V. Arvind, Weinberger, Nir
We investigate the fundamental limits of reliable communication over multi-view channels, in which the channel output is comprised of a large number of independent noisy views of a transmitted symbol. We consider first the setting of multi-view discr
Externí odkaz:
http://arxiv.org/abs/2405.07264
Autor:
Uzan, Neria, Weinberger, Nir
We propose a game-based formulation for learning dimensionality-reducing representations of feature vectors, when only a prior knowledge on future prediction tasks is available. In this game, the first player chooses a representation, and then the se
Externí odkaz:
http://arxiv.org/abs/2403.06971
We consider a statistical version of curriculum learning (CL) in a parametric prediction setting. The learner is required to estimate a target parameter vector, and can adaptively collect samples from either the target model, or other source models t
Externí odkaz:
http://arxiv.org/abs/2402.13366
Whenever inspected by humans, reconstructed signals should not be distinguished from real ones. Typically, such a high perceptual quality comes at the price of high reconstruction error, and vice versa. We study this distortion-perception (DP) tradeo
Externí odkaz:
http://arxiv.org/abs/2402.02265
In continual learning, catastrophic forgetting is affected by multiple aspects of the tasks. Previous works have analyzed separately how forgetting is affected by either task similarity or overparameterization. In contrast, our paper examines how tas
Externí odkaz:
http://arxiv.org/abs/2401.12617
Neural network (NN) denoisers are an essential building block in many common tasks, ranging from image reconstruction to image generation. However, the success of these models is not well understood from a theoretical perspective. In this paper, we a
Externí odkaz:
http://arxiv.org/abs/2311.06748