no code implementations • NeurIPS 2019 • Ali Kavis, Kfir. Y. Levy, Francis Bach, Volkan Cevher
To the best of our knowledge, this is the first adaptive, unified algorithm that achieves the optimal rates in the constrained setting.
1 code implementation • NeurIPS 2020 • Sebastian Curi, Kfir. Y. Levy, Stefanie Jegelka, Andreas Krause
In high-stakes machine learning applications, it is crucial to not only perform well on average, but also when restricted to difficult examples.
no code implementations • ICLR 2019 • Paulina Grnarova, Kfir. Y. Levy, Aurelien Lucchi, Nathanael Perraudin, Thomas Hofmann, Andreas Krause
Generative Adversarial Networks (GANs) have shown great results in accurately modeling complex distributions, but their training is known to be difficult due to instabilities caused by a challenging minimax optimization problem.
1 code implementation • 29 Mar 2019 • Zalán Borsos, Sebastian Curi, Kfir. Y. Levy, Andreas Krause
Adaptive importance sampling for stochastic optimization is a promising approach that offers improved convergence through variance reduction.
no code implementations • 21 Feb 2019 • Pragnya Alatur, Kfir. Y. Levy, Andreas Krause
We consider a setting where multiple players sequentially choose among a common set of actions (arms).
no code implementations • 5 Feb 2019 • Francis Bach, Kfir. Y. Levy
We consider variational inequalities coming from monotone operators, a setting that includes convex minimization and convex-concave saddle-point problems.
1 code implementation • NeurIPS 2019 • Paulina Grnarova, Kfir. Y. Levy, Aurelien Lucchi, Nathanael Perraudin, Ian Goodfellow, Thomas Hofmann, Andreas Krause
Evaluations are essential for: (i) relative assessment of different models and (ii) monitoring the progress of a single model throughout training.
no code implementations • NeurIPS 2018 • Kfir. Y. Levy, Alp Yurtsever, Volkan Cevher
We present a novel method for convex unconstrained optimization that, without any modifications, ensures: (i) accelerated convergence rate for smooth objectives, (ii) standard convergence rate in the general (non-smooth) setting, and (iii) standard convergence rate in the stochastic optimization setting.
no code implementations • 19 Jun 2018 • Sebastian Curi, Kfir. Y. Levy, Andreas Krause
To this end, we introduce a novel estimation algorithm that explicitly trades off bias and variance to optimally reduce the overall estimation error.
no code implementations • 17 May 2018 • Jacob Abernethy, Kevin A. Lai, Kfir. Y. Levy, Jun-Kun Wang
We consider the use of no-regret algorithms to compute equilibria for particular classes of convex-concave games.
2 code implementations • 13 Feb 2018 • Zalán Borsos, Andreas Krause, Kfir. Y. Levy
Modern stochastic optimization methods often rely on uniform sampling which is agnostic to the underlying characteristics of the data.
1 code implementation • NeurIPS 2017 • An Bian, Kfir. Y. Levy, Andreas Krause, Joachim M. Buhmann
Concretely, we first devise a "two-phase" algorithm with $1/4$ approximation guarantee.
1 code implementation • ICLR 2018 • Paulina Grnarova, Kfir. Y. Levy, Aurelien Lucchi, Thomas Hofmann, Andreas Krause
We consider the problem of training generative models with a Generative Adversarial Network (GAN).
no code implementations • NeurIPS 2017 • Kfir. Y. Levy
We present an approach towards convex optimization that relies on a novel scheme which converts online adaptive algorithms into offline methods.
no code implementations • NeurIPS 2016 • Oren Anava, Kfir. Y. Levy
The weighted k-nearest neighbors algorithm is one of the most fundamental non-parametric methods in pattern recognition and machine learning.
no code implementations • 15 Nov 2016 • Kfir. Y. Levy
A commonly used heuristic in non-convex optimization is Normalized Gradient Descent (NGD) - a variant of gradient descent in which only the direction of the gradient is taken into account and its magnitude ignored.
no code implementations • NeurIPS 2015 • Elad Hazan, Kfir. Y. Levy, Shai Shalev-Shwartz
The Normalized Gradient Descent (NGD) algorithm, is an adaptation of Gradient Descent, which updates according to the direction of the gradients, rather than the gradients themselves.
1 code implementation • 12 Mar 2015 • Elad Hazan, Kfir. Y. Levy, Shai Shalev-Shwartz
We extend our algorithm and analysis to the setting of stochastic non-convex optimization with noisy gradient feedback, attaining the same convergence rate.
no code implementations • 15 May 2014 • Elad Hazan, Tomer Koren, Kfir. Y. Levy
We show that in contrast to known asymptotic bounds, as long as the number of prediction/optimization iterations is sub exponential, the logistic loss provides no improvement over a generic non-smooth loss function such as the hinge loss.