Zobrazeno 1 - 10
of 28
pro vyhledávání: '"Nguyen, Huy Lê"'
Autor:
Nguyen, Thien Hang, Nguyen, Huy Le
We introduce two complementary techniques for efficient adaptive optimization that reduce memory requirements while accelerating training of large-scale neural networks. The first technique, Subset-Norm adaptive step size, generalizes AdaGrad-Norm an
Externí odkaz:
http://arxiv.org/abs/2411.07120
Estimating frequencies of elements appearing in a data stream is a key task in large-scale data analysis. Popular sketching approaches to this problem (e.g., CountMin and CountSketch) come with worst-case guarantees that probabilistically bound the e
Externí odkaz:
http://arxiv.org/abs/2312.07535
We give improved tradeoffs between space and regret for the online learning with expert advice problem over $T$ days with $n$ experts. Given a space budget of $n^{\delta}$ for $\delta \in (0,1)$, we provide an algorithm achieving regret $\tilde{O}(n^
Externí odkaz:
http://arxiv.org/abs/2303.01453
In this work, we describe a generic approach to show convergence with high probability for both stochastic convex and non-convex optimization with sub-Gaussian noise. In previous works for convex optimization, either the convergence is only in expect
Externí odkaz:
http://arxiv.org/abs/2302.14843
While the convergence behaviors of stochastic gradient methods are well understood \emph{in expectation}, there still exist many gaps in the understanding of their convergence with \emph{high probability}, where the convergence rate has a logarithmic
Externí odkaz:
http://arxiv.org/abs/2302.05437
We consider the problem of clustering in the learning-augmented setting, where we are given a data set in $d$-dimensional Euclidean space, and a label for each data point given by an oracle indicating what subsets of points should be clustered togeth
Externí odkaz:
http://arxiv.org/abs/2210.17028
In this work, we study the problem of privately maximizing a submodular function in the streaming setting. Extensive work has been done on privately maximizing submodular functions in the general case when the function depends upon the private data o
Externí odkaz:
http://arxiv.org/abs/2210.14315
Recently a multi-agent variant of the classical multi-armed bandit was proposed to tackle fairness issues in online learning. Inspired by a long line of work in social choice and economics, the goal is to optimize the Nash social welfare instead of t
Externí odkaz:
http://arxiv.org/abs/2209.11817
We study the problem of fairness in k-centers clustering on data with disjoint demographic groups. Specifically, this work proposes a variant of fairness which restricts each group's number of centers with both a lower bound (minority-protection) and
Externí odkaz:
http://arxiv.org/abs/2207.11337
Deep neural networks trained by minimizing the average risk can achieve strong average performance. Still, their performance for a subgroup may degrade if the subgroup is underrepresented in the overall data population. Group distributionally robust
Externí odkaz:
http://arxiv.org/abs/2204.09583