Zobrazeno 1 - 10
of 8 250
pro vyhledávání: '"Rosenblatt, P."'
Autor:
Rosenblatt, Lucas, Witter, R. Teal
Fair predictive algorithms hinge on both equality and trust, yet inherent uncertainty in real-world data challenges our ability to make consistent, fair, and calibrated decisions. While fairly managing predictive error has been extensively explored,
Externí odkaz:
http://arxiv.org/abs/2410.02005
We study the problem of approximately recovering a probability distribution given noisy measurements of its Chebyshev polynomial moments. We sharpen prior work, proving that accurate recovery in the Wasserstein distance is possible with more noise th
Externí odkaz:
http://arxiv.org/abs/2408.12385
Autor:
Hébert-Dufresne, Laurent, Kling, Matthew M., Rosenblatt, Samuel F., Miller, Stephanie N., Burnham, P. Alexander, Landry, Nicholas W., Gotelli, Nicholas J., McGill, Brian J.
Stochastic diffusion is the noisy and uncertain process through which dynamics like epidemics, or agents like animal species, disperse over a larger area. Understanding these processes is becoming increasingly important as we attempt to better prepar
Externí odkaz:
http://arxiv.org/abs/2408.07755
Autor:
Premakumar, Vickram N., Vaiana, Michael, Pop, Florin, Rosenblatt, Judd, de Lucena, Diogo Schwerz, Ziman, Kirsten, Graziano, Michael S. A.
Self-models have been a topic of great interest for decades in studies of human cognition and more recently in machine learning. Yet what benefits do self-models confer? Here we show that when artificial networks learn to predict their internal state
Externí odkaz:
http://arxiv.org/abs/2407.10188
Autor:
Parrish, Andrew, Rosenblatt, Joseph
We investigate the almost everywhere convergence of sequences of convolution operators given by probability measures $\mu_n$ on $\mathbb R$. If this sequence of operators constitutes an approximate identity on a particular class of functions $\mathca
Externí odkaz:
http://arxiv.org/abs/2407.09406
In this paper, we investigate the degree to which fine-tuning in Large Language Models (LLMs) effectively mitigates versus merely conceals undesirable behavior. Through the lens of semi-realistic role-playing exercises designed to elicit such behavio
Externí odkaz:
http://arxiv.org/abs/2406.19552
Autor:
Wolfe, Robert, Slaughter, Isaac, Han, Bin, Wen, Bingbing, Yang, Yiwei, Rosenblatt, Lucas, Herman, Bernease, Brown, Eva, Qu, Zening, Weber, Nic, Howe, Bill
The rapid proliferation of generative AI has raised questions about the competitiveness of lower-parameter, locally tunable, open-weight models relative to high-parameter, API-guarded, closed-weight models in terms of performance, domain adaptation,
Externí odkaz:
http://arxiv.org/abs/2405.16820
For an ergodic map $T$ and a non-constant, real-valued $f \in L^1$, the ergodic averages $\mathbb{A}_N f(x) = \frac{1} {N} \sum_{n=1}^N f(T^n x)$ converge a.e., but the convergence is never monotone. Depending on particular properties of the function
Externí odkaz:
http://arxiv.org/abs/2404.11507
Autor:
Rosenblatt, Daniel
We review results of {\v{S}}ver\'{a}k, and Goldstein-Haj{\l}asz-Pakzad on how to show the continuity of functions in a critical Sobolev space with positive Jacobian. In the final chapter we expand on the theory of $VMO$ functions, showing a version o
Externí odkaz:
http://arxiv.org/abs/2401.06253
Differentially private (DP) mechanisms have been deployed in a variety of high-impact social settings (perhaps most notably by the U.S. Census). Since all DP mechanisms involve adding noise to results of statistical queries, they are expected to impa
Externí odkaz:
http://arxiv.org/abs/2312.11712