Zobrazeno 1 - 10
of 124
pro vyhledávání: '"Abernethy, Jacob"'
We theoretically and empirically study the logical reasoning capabilities of LLMs in the context of the Boolean satisfiability (SAT) problem. First, we construct a decoder-only Transformer that can solve SAT using backtracking and deduction via Chain
Externí odkaz:
http://arxiv.org/abs/2410.07432
A lexicographic maximum of a set $X \subseteq \mathbb{R}^n$ is a vector in $X$ whose smallest component is as large as possible, and subject to that requirement, whose second smallest component is as large as possible, and so on for the third smalles
Externí odkaz:
http://arxiv.org/abs/2405.01387
Riemannian convex optimization and minimax optimization have recently drawn considerable attention. Their appeal lies in their capacity to adeptly manage the non-convexity of the objective function as well as constraints inherent in the feasible set
Externí odkaz:
http://arxiv.org/abs/2309.14155
Efficient learning in multi-armed bandit mechanisms such as pay-per-click (PPC) auctions typically involves three challenges: 1) inducing truthful bidding behavior (incentives), 2) using personalization in the users (context), and 3) circumventing ma
Externí odkaz:
http://arxiv.org/abs/2307.07675
Federated learning (FL) is a common and practical framework for learning a machine model in a decentralized fashion. A primary motivation behind this decentralized approach is data privacy, ensuring that the learner never sees the data of each local
Externí odkaz:
http://arxiv.org/abs/2306.11913
The projection operation is a critical component in a wide range of optimization algorithms, such as online gradient descent (OGD), for enforcing constraints and achieving optimal regret bounds. However, it suffers from computational complexity limit
Externí odkaz:
http://arxiv.org/abs/2305.19349
First-order optimization methods tend to inherently favor certain solutions over others when minimizing an underdetermined training objective that has multiple global optima. This phenomenon, known as implicit bias, plays a critical role in understan
Externí odkaz:
http://arxiv.org/abs/2305.17544
We study the phenomenon of \textit{in-context learning} (ICL) exhibited by large language models, where they can adapt to a new learning task, given a handful of labeled examples, without any explicit parameter optimization. Our goal is to explain ho
Externí odkaz:
http://arxiv.org/abs/2305.17040
In this paper, we consider the sequential decision problem where the goal is to minimize the general dynamic regret on a complete Riemannian manifold. The task of offline optimization on such a domain, also known as a geodesic metric space, has recen
Externí odkaz:
http://arxiv.org/abs/2302.08652
The classical algorithms for online learning and decision-making have the benefit of achieving the optimal performance guarantees, but suffer from computational complexity limitations when implemented at scale. More recent sophisticated techniques, w
Externí odkaz:
http://arxiv.org/abs/2210.09385