Zobrazeno 1 - 10
of 1 760
pro vyhledávání: '"JORDAN, MICHAEL I."'
We present differentially private algorithms for high-dimensional mean estimation. Previous private estimators on distributions over $\mathbb{R}^d$ suffer from a curse of dimensionality, as they require $\Omega(d^{1/2})$ samples to achieve non-trivia
Externí odkaz:
http://arxiv.org/abs/2411.00775
Autor:
Aliakbarpour, Maryam, Chaudhuri, Syomantak, Courtade, Thomas A., Fallah, Alireza, Jordan, Michael I.
Local Differential Privacy (LDP) offers strong privacy guarantees without requiring users to trust external parties. However, LDP applies uniform protection to all data features, including less sensitive ones, which degrades performance of downstream
Externí odkaz:
http://arxiv.org/abs/2410.18404
Autor:
Scheid, Antoine, Boursier, Etienne, Durmus, Alain, Jordan, Michael I., Ménard, Pierre, Moulines, Eric, Valko, Michal
Reinforcement Learning from Human Feedback (RLHF) has become a popular approach to align language models (LMs) with human preferences. This method involves collecting a large dataset of human pairwise preferences across various text generations and u
Externí odkaz:
http://arxiv.org/abs/2410.17055
Practitioners have consistently observed three puzzling phenomena in transformer-based large language models (LLMs): attention sinks, value-state drains, and residual-state peaks, collectively referred to as extreme-token phenomena. These phenomena a
Externí odkaz:
http://arxiv.org/abs/2410.13835
Emerging marketplaces for large language models and other large-scale machine learning (ML) models appear to exhibit market concentration, which has raised concerns about whether there are insurmountable barriers to entry in such markets. In this wor
Externí odkaz:
http://arxiv.org/abs/2409.03734
We provide a unified analysis of two-timescale gradient descent ascent (TTGDA) for solving structured nonconvex minimax optimization problems in the form of $\min_\textbf{x} \max_{\textbf{y} \in Y} f(\textbf{x}, \textbf{y})$, where the objective func
Externí odkaz:
http://arxiv.org/abs/2408.11974
Autor:
Capitaine, Aymeric, Boursier, Etienne, Scheid, Antoine, Moulines, Eric, Jordan, Michael I., El-Mhamdi, El-Mahdi, Durmus, Alain
Collaborative learning offers a promising avenue for leveraging decentralized data. However, collaboration in groups of strategic learners is not a given. In this work, we consider strategic agents who wish to train a model together but have sampling
Externí odkaz:
http://arxiv.org/abs/2407.14332
Autor:
Scheid, Antoine, Capitaine, Aymeric, Boursier, Etienne, Moulines, Eric, Jordan, Michael I, Durmus, Alain
In economic theory, the concept of externality refers to any indirect effect resulting from an interaction between players that affects the social welfare. Most of the models within which externality has been studied assume that agents have perfect k
Externí odkaz:
http://arxiv.org/abs/2406.19824
Science and technology have a growing need for effective mechanisms that ensure reliable, controlled performance from black-box machine learning algorithms. These performance guarantees should ideally hold conditionally on the input-that is the perfo
Externí odkaz:
http://arxiv.org/abs/2406.17819
We study collaborative learning systems in which the participants are competitors who will defect from the system if they lose revenue by collaborating. As such, we frame the system as a duopoly of competitive firms who are each engaged in training m
Externí odkaz:
http://arxiv.org/abs/2406.15898