Zobrazeno 1 - 10
of 17
pro vyhledávání: '"Pabbaraju, Chirag"'
Credit attribution is crucial across various fields. In academic research, proper citation acknowledges prior work and establishes original contributions. Similarly, in generative models, such as those trained on existing artworks or music, it is imp
Externí odkaz:
http://arxiv.org/abs/2406.15916
Recent advances in large language models have shown capabilities that are extraordinary and near-superhuman. These models operate with such complexity that reliably evaluating and aligning them proves challenging for humans. This leads to the natural
Externí odkaz:
http://arxiv.org/abs/2405.15116
Given an arbitrary set of high dimensional points in $\ell_1$, there are known negative results that preclude the possibility of always mapping them to a low dimensional $\ell_1$ space while preserving distances with small multiplicative distortion.
Externí odkaz:
http://arxiv.org/abs/2312.02435
We examine the extent to which sublinear-sample property testing and estimation applies to settings where samples are independently but not identically distributed. Specifically, we consider the following distributional property testing framework: Su
Externí odkaz:
http://arxiv.org/abs/2311.11194
We propose a simple generalization of standard and empirically successful decision tree learning algorithms such as ID3, C4.5, and CART. These algorithms, which have been central to machine learning for decades, are greedy in nature: they grow a deci
Externí odkaz:
http://arxiv.org/abs/2310.01551
Autor:
Pabbaraju, Chirag
A hypothesis class admits a sample compression scheme, if for every sample labeled by a hypothesis from the class, it is possible to retain only a small subsample, using which the labels on the entire sample can be inferred. The size of the compressi
Externí odkaz:
http://arxiv.org/abs/2308.06424
Autor:
Pabbaraju, Chirag, Rohatgi, Dhruv, Sevekari, Anish, Lee, Holden, Moitra, Ankur, Risteski, Andrej
Score matching is an alternative to maximum likelihood (ML) for estimating a probability distribution parametrized up to a constant of proportionality. By fitting the ''score'' of the distribution, it sidesteps the need to compute this constant of pr
Externí odkaz:
http://arxiv.org/abs/2306.01993
Autor:
Charikar, Moses, Pabbaraju, Chirag
A classical result in learning theory shows the equivalence of PAC learnability of binary hypothesis classes and the finiteness of VC dimension. Extending this to the multiclass setting was an open problem, which was settled in a recent breakthrough
Externí odkaz:
http://arxiv.org/abs/2211.04956
Noise Contrastive Estimation (NCE) is a popular approach for learning probability density functions parameterized up to a constant of proportionality. The main idea is to design a classification problem for distinguishing training data from samples f
Externí odkaz:
http://arxiv.org/abs/2210.00189
Normalizing flows are a widely used class of latent-variable generative models with a tractable likelihood. Affine-coupling (Dinh et al, 2014-16) models are a particularly common type of normalizing flows, for which the Jacobian of the latent-to-obse
Externí odkaz:
http://arxiv.org/abs/2107.02951