7 citations · 12 across the 18 of their papers we have counts for
10 papers · 1 filter
OpenThoughts: Data Recipes for Reasoning Models
Etash Guha, Ryan Marten, Sedrick Keh +47
Reasoning models have made rapid progress on many benchmarks involving math, code, and science. Yet, there are still many open questions about the best training recipes for reasoni…
Archon: An Architecture Search Framework for Inference-Time Techniques
Jon Saad-Falcon, Adrian Gamarra Lafuente, Shlok Natarajan +8
Inference-time techniques, such as repeated sampling or iterative revisions, are emerging as powerful ways to enhance large-language models (LLMs) at test time. However, best pract…
DataComp-LM: In search of the next generation of training sets for language models
Jeffrey Li, Alex Fang, Georgios Smyrnis +56
We introduce DataComp for Language Models (DCLM), a testbed for controlled dataset experiments with the goal of improving language models. As part of DCLM, we provide a standardize…
Conformal Prediction via Regression-as-Classification
Etash Guha, Shlok Natarajan, Thomas Möllenhoff +2
Conformal prediction (CP) for regression can be challenging, especially when the output distribution is heteroscedastic, multimodal, or skewed. Some of the issues can be addressed…
On the Diminishing Returns of Width for Continual Learning
Etash Guha, Vihan Lakshman
While deep neural networks have demonstrated groundbreaking performance in various settings, these models often suffer from \emph{catastrophic forgetting} when trained on new tasks…
Conformalization of Sparse Generalized Linear Models
Etash Kumar Guha, Eugene Ndiaye, Xiaoming Huo
Given a sequence of observable variables , the conformal prediction method estimates a confidence set for given that is vali…
Generalization Bounds for Magnitude-Based Pruning via Sparse Matrix Sketching
Etash Kumar Guha, Prasanjit Dubey, Xiaoming Huo
In this paper, we derive a novel bound on the generalization error of Magnitude-Based pruning of overparameterized neural networks. Our work builds on the bounds in Arora et al. [2…
Solving Robust MDPs through No-Regret Dynamics
Etash Kumar Guha
Reinforcement Learning is a powerful framework for training agents to navigate different situations, but it is susceptible to changes in environmental dynamics. However, solving Ma…
On Accelerated Perceptrons and Beyond
Guanghui Wang, Rafael Hanashiro, Etash Guha +1
The classical Perceptron algorithm of Rosenblatt can be used to find a linear threshold function to correctly classify linearly separable data points, assuming the classes are…
Annealed Training for Combinatorial Optimization on Graphs
Haoran Sun, Etash K. Guha, Hanjun Dai
The hardness of combinatorial optimization (CO) problems hinders collecting solutions for supervised learning. However, learning neural networks for CO problems is notoriously diff…