
AutoAssist: A Framework to Accelerate Training of Deep Neural Networks
Deep neural networks have yielded superior performance in many applicati...
read it

Inverting Deep Generative models, One layer at a time
We study the problem of inverting a deep generative model with ReLU acti...
read it

The Limitations of Adversarial Training and the BlindSpot Attack
The adversarial training procedure proposed by Madry et al. (2018) is on...
read it

Multiresolution Transformer Networks: Recurrence is Not Essential for Modeling Hierarchical Structure
The architecture of Transformer is based entirely on selfattention, and...
read it

PrimalDual Block FrankWolfe
We propose a variant of the FrankWolfe algorithm for solving a class of...
read it

Recovery Guarantees for Onehiddenlayer Neural Networks
In this paper, we consider regression problems with onehiddenlayer neu...
read it

Similarity Preserving Representation Learning for Time Series Analysis
A considerable amount of machine learning algorithms take instancefeatu...
read it

Generalized Root Models: Beyond Pairwise Graphical Models for Univariate Exponential Families
We present a novel kway highdimensional graphical model called the Gen...
read it

Extreme Stochastic Variational Inference: Distributed and Asynchronous
We propose extreme stochastic variational inference (ESVI), an asynchron...
read it

Square Root Graphical Models: Multivariate Generalizations of Univariate Exponential Families that Permit Positive Dependencies
We develop Square Root Graphical Models (SQR), a novel class of parametr...
read it

Highdimensional Time Series Prediction with Missing Values
Highdimensional time series prediction is needed in applications as div...
read it

Optimal DecisionTheoretic Classification Using NonDecomposable Performance Metrics
We provide a general theoretical analysis of expected outofsample util...
read it

PU Learning for Matrix Completion
In this paper, we consider the matrix completion problem when the observ...
read it

Proximal QuasiNewton for Computationally Intensive L1regularized Mestimators
We consider the class of optimization problems arising from computationa...
read it

Sparse Inverse Covariance Matrix Estimation Using Quadratic Approximation
The L1regularized Gaussian maximum likelihood estimator (MLE) has been ...
read it

Provable Inductive Matrix Completion
Consider a movie recommendation system where apart from the ratings info...
read it

Orthogonal Matching Pursuit with Replacement
In this paper, we consider the problem of compressed sensing where the g...
read it

Metric and Kernel Learning using a Linear Transformation
Metric and kernel learning are important in several machine learning app...
read it

Learning Nonoverlapping Convolutional Neural Networks with Multiple Kernels
In this paper, we consider parameter recovery for nonoverlapping convol...
read it

Learning Long Term Dependencies via Fourier Recurrent Units
It is a known fact that training recurrent neural networks for tasks tha...
read it

Stabilizing Gradients for Deep Neural Networks via Efficient SVD Parameterization
Vanishing and exploding gradients are two of the main obstacles in train...
read it

Nonlinear Inductive Matrix Completion based on Onelayer Neural Networks
The goal of a recommendation system is to predict the interest of a user...
read it

Towards Fast Computation of Certified Robustness for ReLU Networks
Verifying the robustness property of a general Rectified Linear Unit (Re...
read it

Discrete Attacks and Submodular Optimization with Applications to Text Classification
Adversarial examples are carefully constructed modifications to an input...
read it

SysML: The New Frontier of Machine Learning Systems
Machine learning (ML) techniques are enjoying rapidly increasing adoptio...
read it
Inderjit S. Dhillon
is this you? claim profile
Gottesman Family Centennial Professor at UT Austin and Amazon Fellow