Search Results for author: Garud Iyengar

Found 10 papers, 1 papers with code

Multinomial Logit Contextual Bandits: Provable Optimality and Practicality

no code implementations25 Mar 2021 Min-hwan Oh, Garud Iyengar

We propose upper confidence bound based algorithms for this MNL contextual bandit.

Multi-Armed Bandits

Sparsity-Agnostic Lasso Bandit

no code implementations16 Jul 2020 Min-hwan Oh, Garud Iyengar, Assaf Zeevi

We consider a stochastic contextual bandit problem where the dimension $d$ of the feature vectors is potentially large, however, only a sparse subset of features of cardinality $s_0 \ll d$ affect the reward function.

Glycan processing in the Golgi -- optimal information coding and constraints on cisternal number and enzyme specificity

no code implementations18 May 2020 Alkesh Yadav, Quentin Vagne, Pierre Sens, Garud Iyengar, Madan Rao

In this paper, we quantitatively analyse the tradeoffs between the number of cisternae and the number and specificity of enzymes, in order to synthesize a prescribed target glycan distribution of a certain complexity.

Sequential Anomaly Detection using Inverse Reinforcement Learning

no code implementations22 Apr 2020 Min-hwan Oh, Garud Iyengar

In order to construct a reliable anomaly detection method and take into consideration the confidence of the predicted anomaly score, we adopt a Bayesian approach for IRL.

Anomaly Detection Decision Making

Directed Exploration in PAC Model-Free Reinforcement Learning

no code implementations31 Aug 2018 Min-hwan Oh, Garud Iyengar

We study an exploration method for model-free RL that generalizes the counter-based exploration bonus methods and takes into account long term exploratory value of actions rather than a single step look-ahead.

Efficient Exploration Q-Learning

Robust Implicit Backpropagation

no code implementations7 Aug 2018 Francois Fagan, Garud Iyengar

Arguably the biggest challenge in applying neural networks is tuning the hyperparameters, in particular the learning rate.

Unbiased scalable softmax optimization

no code implementations ICLR 2018 Francois Fagan, Garud Iyengar

Recent neural network and language models rely on softmax distributions with an extremely large number of categories.

An Asynchronous Distributed Proximal Gradient Method for Composite Convex Optimization

no code implementations30 Sep 2014 Necdet Serhat Aybat, Garud Iyengar, Zi Wang

We propose a distributed first-order augmented Lagrangian (DFAL) algorithm to minimize the sum of composite convex functions, where each term in the sum is a private cost function belonging to a node, and only nodes connected by an edge can directly communicate with each other.

Optimization and Control

Fast First-Order Methods for Stable Principal Component Pursuit

no code implementations11 May 2011 Necdet Serhat Aybat, Donald Goldfarb, Garud Iyengar

The stable principal component pursuit (SPCP) problem is a non-smooth convex optimization problem, the solution of which has been shown both in theory and in practice to enable one to recover the low rank and sparse components of a matrix whose elements have been corrupted by Gaussian noise.

Optimization and Control

Cannot find the paper you are looking for? You can Submit a new open access paper.