activity
20192026
collaborators
Showing cs.LGShow all

10 papers · 1 filter

cs.LG2026

Agnostic Language Identification and Generation

Mikael Møller Høgsgaard, Chirag Pabbaraju

Recent works on language identification and generation have established tight statistical rates at which these tasks can be achieved. These works typically operate under a strong r…

cs.LG2025

Relating Misfit to Gain in Weak-to-Strong Generalization Beyond the Squared Loss

Abhijeet Mulgund, Chirag Pabbaraju

The paradigm of weak-to-strong generalization constitutes the training of a strong AI model on data labeled by a weak AI model, with the goal that the strong model nevertheless out…

cs.LG2024

Quantifying the Gain in Weak-to-Strong Generalization

Moses Charikar, Chirag Pabbaraju, Kirankumar Shiragur

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…

cs.LG2023

Harnessing the Power of Choices in Decision Tree Learning

Guy Blanc, Jane Lange, Chirag Pabbaraju +3

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 t…

cs.LG2023

Multiclass Learnability Does Not Imply Sample Compression

Chirag Pabbaraju

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…

cs.LG2023

Provable benefits of score matching

Chirag Pabbaraju, Dhruv Rohatgi, Anish Sevekari +3

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…