Zobrazeno 1 - 10
of 4 919
pro vyhledávání: '"Santosh S"'
Autor:
Kook, Yunbum, Vempala, Santosh S.
We study the complexity of sampling, rounding, and integrating arbitrary logconcave functions. Our new approach provides the first complexity improvements in nearly two decades for general logconcave functions for all three problems, and matches the
Externí odkaz:
http://arxiv.org/abs/2411.13462
Autor:
Reid, Mirabel, Vempala, Santosh S.
As Large Language Models (LLMs) perform (and sometimes excel at) more and more complex cognitive tasks, a natural question is whether AI really understands. The study of understanding in LLMs is in its infancy, and the community has yet to incorporat
Externí odkaz:
http://arxiv.org/abs/2406.14722
How intelligence arises from the brain is a central problem in science. A crucial aspect of intelligence is dealing with uncertainty -- developing good predictions about one's environment, and converting these predictions into decisions. The brain it
Externí odkaz:
http://arxiv.org/abs/2406.07715
We present a new random walk for uniformly sampling high-dimensional convex bodies. It achieves state-of-the-art runtime complexity with stronger guarantees on the output than previously known, namely in R\'enyi divergence (which implies TV, $\mathca
Externí odkaz:
http://arxiv.org/abs/2405.01425
Recent language models generate false but plausible-sounding text with surprising frequency. Such "hallucinations" are an obstacle to the usability of language-based AI systems and can harm people who rely upon their outputs. This work shows that the
Externí odkaz:
http://arxiv.org/abs/2311.14648
Autor:
Verma, Dhruv, Bhalla, Sejal, Santosh, S. V. Sai, Yadav, Saumya, Parnami, Aman, Shukla, Jainendra
Student attention is an indispensable input for uncovering their goals, intentions, and interests, which prove to be invaluable for a multitude of research areas, ranging from psychology to interactive systems. However, most existing methods to class
Externí odkaz:
http://arxiv.org/abs/2311.02924
Autor:
Cao, Xinyuan, Vempala, Santosh S.
We give a polynomial-time algorithm for learning high-dimensional halfspaces with margins in $d$-dimensional space to within desired TV distance when the ambient distribution is an unknown affine transformation of the $d$-fold product of an (unknown)
Externí odkaz:
http://arxiv.org/abs/2311.01435
Autor:
Peng, Richard1 (AUTHOR) yangp@cs.cmu.edu, Vempala, Santosh S.2 (AUTHOR) vempala@gatech.edu
Publikováno v:
Communications of the ACM. Jul2024, Vol. 67 Issue 7, p79-86. 8p.
Autor:
Kook, Yunbum, Vempala, Santosh S.
The connections between (convex) optimization and (logconcave) sampling have been considerably enriched in the past decade with many conceptual and mathematical analogies. For instance, the Langevin algorithm can be viewed as a sampling analogue of g
Externí odkaz:
http://arxiv.org/abs/2307.12943
Even as machine learning exceeds human-level performance on many applications, the generality, robustness, and rapidity of the brain's learning capabilities remain unmatched. How cognition arises from neural activity is a central open question in neu
Externí odkaz:
http://arxiv.org/abs/2306.03812