Despite the empirical success and practical significance of (relational)...
In stochastic zeroth-order optimization, a problem of practical relevanc...
Understanding when and how much a model gradient leaks information about...
We propose COEP, an automated and principled framework to solve inverse
...
High-performance deep learning methods typically rely on large annotated...
Influence Maximization (IM), which aims to select a set of users from a
...
We give novel algorithms for multi-task and lifelong linear bandits with...
Data augmentation is popular in the training of large neural networks;
c...
The goal of Knowledge Tracing (KT) is to estimate how well students have...
Hierarchical reinforcement learning (HRL) has seen widespread interest a...
Deep Reinforcement Learning (RL) powered by neural net approximation of ...
Bandit problems with linear or concave reward have been extensively stud...
Eluder dimension and information gain are two widely used methods of
com...
Representation learning has been widely studied in the context of
meta-l...
One of the central problems in machine learning is domain adaptation. Un...
Sampling is a fundamental and arguably very important task with numerous...
Self-supervised representation learning solves auxiliary prediction task...
We propose signed splitting steepest descent (S3D), which progressively ...
We study image inverse problems with invertible generative priors,
speci...
This paper studies few-shot learning via representation learning, where ...
Adversarial training has become one of the most effective methods for
im...
In a recent series of papers it has been established that variants of
Gr...
Large-scale machine learning training suffers from two prior challenges,...
Generative adversarial networks (GANs) are a widely used framework for
l...
We study the problem of inverting a deep generative model with ReLU
acti...
We propose a variant of the Frank-Wolfe algorithm for solving a class of...
Adversarial examples are carefully constructed modifications to an input...
Time series data analytics has been a problem of substantial interests f...
Vanishing and exploding gradients are two of the main obstacles in train...
Large batch size training of Neural Networks has been shown to incur acc...
A considerable amount of machine learning algorithms take instance-featu...
Given a symmetric nonnegative matrix A, symmetric nonnegative matrix
fac...