Search Results for author: Nikhil Vyas

Found 8 papers, 1 papers with code

Distinguishing the Knowable from the Unknowable with Language Models

1 code implementation5 Feb 2024 Gustaf Ahdritz, Tian Qin, Nikhil Vyas, Boaz Barak, Benjamin L. Edelman

We study the feasibility of identifying epistemic uncertainty (reflecting a lack of knowledge), as opposed to aleatoric uncertainty (reflecting entropy in the underlying distribution), in the outputs of large language models (LLMs) over free-form text.

On Privileged and Convergent Bases in Neural Network Representations

no code implementations24 Jul 2023 Davis Brown, Nikhil Vyas, Yamini Bansal

Our findings give evidence that while Linear Mode Connectivity improves with increased network width, this improvement is not due to an increase in basis correlation.

Linear Mode Connectivity

Beyond Implicit Bias: The Insignificance of SGD Noise in Online Learning

no code implementations14 Jun 2023 Nikhil Vyas, Depen Morwani, Rosie Zhao, Gal Kaplun, Sham Kakade, Boaz Barak

The success of SGD in deep learning has been ascribed by prior works to the implicit bias induced by high learning rate or small batch size ("SGD noise").

On Provable Copyright Protection for Generative Models

no code implementations21 Feb 2023 Nikhil Vyas, Sham Kakade, Boaz Barak

There is a growing concern that learned conditional generative models may output samples that are substantially similar to some copyrighted data $C$ that was in their training set.

Limitations of the NTK for Understanding Generalization in Deep Learning

no code implementations20 Jun 2022 Nikhil Vyas, Yamini Bansal, Preetum Nakkiran

The ``Neural Tangent Kernel'' (NTK) (Jacot et al 2018), and its empirical variants have been proposed as a proxy to capture certain behaviors of real neural networks.

Thwarting Adversarial Examples: An $L_0$-RobustSparse Fourier Transform

no code implementations12 Dec 2018 Mitali Bafna, Jack Murtagh, Nikhil Vyas

We give a new algorithm for approximating the Discrete Fourier transform of an approximately sparse signal that has been corrupted by worst-case $L_0$ noise, namely a bounded number of coordinates of the signal have been corrupted arbitrarily.

General Classification Image Classification

Thwarting Adversarial Examples: An L_0-Robust Sparse Fourier Transform

no code implementations NeurIPS 2018 Mitali Bafna, Jack Murtagh, Nikhil Vyas

We give a new algorithm for approximating the Discrete Fourier transform of an approximately sparse signal that is robust to worst-case $L_0$ corruptions, namely that some coordinates of the signal can be corrupt arbitrarily.

General Classification Image Classification

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