
Representation Learning via Invariant Causal Mechanisms
Selfsupervised learning has emerged as a strategy to reduce the relianc...
read it

EigenGame: PCA as a Nash Equilibrium
We present a novel view on principal component analysis (PCA) as a compe...
read it

Social Diversity and Social Preferences in MixedMotive Reinforcement Learning
Recent research on reinforcement learning in pureconflict and purecomm...
read it

Spectrogram Feature Losses for Music Source Separation
In this paper we study deep learningbased music source separation, and ...
read it

Neural Importance Sampling
We propose to use deep neural networks for generating samples in Monte C...
read it

A Fully Progressive Approach to SingleImage SuperResolution
Recent deep learning approaches to single image superresolution have ac...
read it

PhaseNet for Video Frame Interpolation
Most approaches for video frame interpolation require accurate dense cor...
read it

Deep Scattering: Rendering Atmospheric Clouds with RadiancePredicting Neural Networks
We present a technique for efficiently synthesizing images of atmospheri...
read it

Preserving Differential Privacy Between Features in Distributed Estimation
Privacy is crucial in many applications of machine learning. Legal, ethi...
read it

The Shattered Gradients Problem: If resnets are the answer, then what is the question?
A longstanding obstacle to progress in deep learning is the problem of ...
read it

Scalable Adaptive Stochastic Optimization Using Random Projections
Adaptive stochastic gradient methods such as AdaGrad have gained popular...
read it

Neural Taylor Approximations: Convergence and Exploration in Rectifier Networks
Modern convolutional networks, incorporating rectifiers and maxpooling,...
read it

Variance Reduced Stochastic Gradient Descent with Neighbors
Stochastic Gradient Descent (SGD) is a workhorse in machine learning, ye...
read it

DUALLOCO: Distributing Statistical Estimation Using Random Projections
We present DUALLOCO, a communicationefficient algorithm for distribute...
read it

Correlated random features for fast semisupervised learning
This paper presents Correlated Nystrom Views (XNV), a fast semisupervis...
read it

Subspace clustering of highdimensional data: a predictive approach
In several application domains, highdimensional observations are collec...
read it

Multiview predictive partitioning in high dimensions
Many modern data mining applications are concerned with the analysis of ...
read it