Zobrazeno 1 - 3
of 3
pro vyhledávání: '"Karchmer, Ari"'
Autor:
Karchmer, Ari
Recently, multimodal machine learning has enjoyed huge empirical success (e.g. GPT-4). Motivated to develop theoretical justification for this empirical success, Lu (NeurIPS '23, ALT '24) introduces a theory of multimodal learning, and considers poss
Externí odkaz:
http://arxiv.org/abs/2404.02254
Autor:
Karchmer, Ari
(Abridged) Designing computationally efficient algorithms in the agnostic learning model (Haussler, 1992; Kearns et al., 1994) is notoriously difficult. In this work, we consider agnostic learning with membership queries for touchstone classes at the
Externí odkaz:
http://arxiv.org/abs/2311.06690
Autor:
Karchmer, Ari
Carmosino et al. (2016) demonstrated that natural proofs of circuit lower bounds for $\Lambda$ imply efficient algorithms for learning $\Lambda$-circuits, but only over \textit{the uniform distribution}, with \textit{membership queries}, and provided
Externí odkaz:
http://arxiv.org/abs/2310.03641