Search Results for author:
Found 19 papers, 7 papers with code
UniXGrad: A Universal, Adaptive Algorithm with Optimal Guarantees for Constrained Optimization
To the best of our knowledge, this is the first adaptive, unified algorithm that achieves the optimal rates in the constrained setting.
Adaptive Sampling for Stochastic Risk-Averse Learning
In high-stakes machine learning applications, it is crucial to not only perform well on average, but also when restricted to difficult examples.
Evaluating GANs via Duality
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.
Online Variance Reduction with Mixtures
Adaptive importance sampling for stochastic optimization is a promising approach that offers improved convergence through variance reduction.
Multi-Player Bandits: The Adversarial Case
We consider a setting where multiple players sequentially choose among a common set of actions (arms).
A Universal Algorithm for Variational Inequalities Adaptive to Smoothness and Noise
We consider variational inequalities coming from monotone operators, a setting that includes convex minimization and convex-concave saddle-point problems.
A domain agnostic measure for monitoring and evaluating GANs
Evaluations are essential for: (i) relative assessment of different models and (ii) monitoring the progress of a single model throughout training.
Online Adaptive Methods, Universality and Acceleration
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.
Adaptive Input Estimation in Linear Dynamical Systems with Applications to Learning-from-Observations
To this end, we introduce a novel estimation algorithm that explicitly trades off bias and variance to optimally reduce the overall estimation error.
Faster Rates for Convex-Concave Games
We consider the use of no-regret algorithms to compute equilibria for particular classes of convex-concave games.
Online Variance Reduction for Stochastic Optimization
Modern stochastic optimization methods often rely on uniform sampling which is agnostic to the underlying characteristics of the data.
Continuous DR-submodular Maximization: Structure and Algorithms
Concretely, we first devise a "two-phase" algorithm with $1/4$ approximation guarantee.
An Online Learning Approach to Generative Adversarial Networks
We consider the problem of training generative models with a Generative Adversarial Network (GAN).
Online to Offline Conversions, Universality and Adaptive Minibatch Sizes
We present an approach towards convex optimization that relies on a novel scheme which converts online adaptive algorithms into offline methods.
k*-Nearest Neighbors: From Global to Local
The weighted k-nearest neighbors algorithm is one of the most fundamental non-parametric methods in pattern recognition and machine learning.
The Power of Normalization: Faster Evasion of Saddle Points
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.
Beyond Convexity: Stochastic Quasi-Convex Optimization
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.
On Graduated Optimization for Stochastic Non-Convex Problems
We extend our algorithm and analysis to the setting of stochastic non-convex optimization with noisy gradient feedback, attaining the same convergence rate.
Logistic Regression: Tight Bounds for Stochastic and Online Optimization
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.
