
-
Underspecification Presents Challenges for Credibility in Modern Machine Learning
ML models often exhibit unexpectedly poor behavior when they are deploye...
read it
-
A Sober Look at the Unsupervised Learning of Disentangled Representations and their Evaluation
The idea behind the unsupervised learning of disentangled representation...
read it
-
Which Model to Transfer? Finding the Needle in the Growing Haystack
Transfer learning has been recently popularized as a data-efficient alte...
read it
-
Representation learning from videos in-the-wild: An object-centric approach
We propose a method to learn image representations from uncurated videos...
read it
-
A Commentary on the Unsupervised Learning of Disentangled Representations
The goal of the unsupervised learning of disentangled representations is...
read it
-
On Robustness and Transferability of Convolutional Neural Networks
Modern deep convolutional networks (CNNs) are often criticized for not g...
read it
-
Self-Supervised Learning of Video-Induced Visual Invariances
We propose a general framework for self-supervised learning of transfera...
read it
-
Semantic Bottleneck Scene Generation
Coupling the high-fidelity generation capabilities of label-conditional ...
read it
-
On Mutual Information Maximization for Representation Learning
Many recent methods for unsupervised or self-supervised representation l...
read it
-
Evaluating Generative Models Using Divergence Frontiers
Despite the tremendous progress in the estimation of generative models, ...
read it
-
High-Fidelity Image Generation With Fewer Labels
Deep generative models are becoming a cornerstone of modern machine lear...
read it
-
Recent Advances in Autoencoder-Based Representation Learning
Learning useful representations with little or no supervision is a key c...
read it
-
Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations
In recent years, the interest in unsupervised learning of disentangled r...
read it
-
Self-Supervised Generative Adversarial Networks
Conditional GANs are at the forefront of natural image synthesis. The ma...
read it
-
On Self Modulation for Generative Adversarial Networks
Training Generative Adversarial Networks (GANs) is notoriously challengi...
read it
-
The GAN Landscape: Losses, Architectures, Regularization, and Normalization
Generative Adversarial Networks (GANs) are a class of deep generative mo...
read it
-
Assessing Generative Models via Precision and Recall
Recent advances in generative modeling have led to an increased interest...
read it
-
Deep Generative Models for Distribution-Preserving Lossy Compression
We propose and study the problem of distribution-preserving lossy compre...
read it
-
Are GANs Created Equal? A Large-Scale Study
Generative adversarial networks (GAN) are a powerful subclass of generat...
read it
-
One-Shot Coresets: The Case of k-Clustering
Scaling clustering algorithms to massive data sets is a challenging task...
read it
-
Stochastic Submodular Maximization: The Case of Coverage Functions
Stochastic optimization of continuous objectives is at the heart of mode...
read it
-
Training Mixture Models at Scale via Coresets
How can we train a statistical mixture model on a massive data set? In t...
read it
-
Practical Coreset Constructions for Machine Learning
We investigate coresets - succinct, small summaries of large data sets -...
read it
-
Uniform Deviation Bounds for Unbounded Loss Functions like k-Means
Uniform deviation bounds limit the difference between a model's expected...
read it
-
Scalable and Distributed Clustering via Lightweight Coresets
Coresets are compact representations of data sets such that models train...
read it
-
Horizontally Scalable Submodular Maximization
A variety of large-scale machine learning problems can be cast as instan...
read it
-
Tradeoffs for Space, Time, Data and Risk in Unsupervised Learning
Faced with massive data, is it possible to trade off (statistical) risk,...
read it
-
Linear-time Outlier Detection via Sensitivity
Outliers are ubiquitous in modern data sets. Distance-based techniques a...
read it
-
Strong Coresets for Hard and Soft Bregman Clustering with Applications to Exponential Family Mixtures
Coresets are efficient representations of data sets such that models tra...
read it