Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Mahankali, Arvind"'
Recent works have empirically analyzed in-context learning and shown that transformers trained on synthetic linear regression tasks can learn to implement ridge regression, which is the Bayes-optimal predictor, given sufficient capacity [Aky\"urek et
Externí odkaz:
http://arxiv.org/abs/2307.03576
Despite recent theoretical progress on the non-convex optimization of two-layer neural networks, it is still an open question whether gradient descent on neural networks without unnatural modifications can achieve better sample complexity than kernel
Externí odkaz:
http://arxiv.org/abs/2306.16361
We study low rank approximation of tensors, focusing on the tensor train and Tucker decompositions, as well as approximations with tree tensor networks and more general tensor networks. For tensor train decomposition, we give a bicriteria $(1 + \eps)
Externí odkaz:
http://arxiv.org/abs/2207.07417
We give the first single-pass streaming algorithm for Column Subset Selection with respect to the entrywise $\ell_p$-norm with $1 \leq p < 2$. We study the $\ell_p$ norm loss since it is often considered more robust to noise than the standard Frobeni
Externí odkaz:
http://arxiv.org/abs/2107.07657
We study the problem of entrywise $\ell_1$ low rank approximation. We give the first polynomial time column subset selection-based $\ell_1$ low rank approximation algorithm sampling $\tilde{O}(k)$ columns and achieving an $\tilde{O}(k^{1/2})$-approxi
Externí odkaz:
http://arxiv.org/abs/2007.10307
We apply a one-dimensional discrete dynamical system originally considered by Arnol'd reminiscent of mathematical billiards to the study of two-move riders, a type of fairy chess piece. In this model, particles travel through a bounded convex region
Externí odkaz:
http://arxiv.org/abs/1901.01917
Publikováno v:
In European Journal of Combinatorics June 2021 95