
Improved Bounds on Minimax Regret under Logarithmic Loss via SelfConcordance
We consider the classical problem of sequential probability assignment u...
read it

On the role of data in PACBayes bounds
The dominant term in PACBayes bounds is often the Kullback–Leibler dive...
read it

Sharpened Generalization Bounds based on Conditional Mutual Information and an Application to Noisy, Iterative Algorithms
The informationtheoretic framework of Russo and J. Zou (2016) and Xu an...
read it

Approximations in Probabilistic Programs
We study the firstorder probabilistic programming language introduced b...
read it

Linear Mode Connectivity and the Lottery Ticket Hypothesis
We introduce "instability analysis," a framework for assessing whether t...
read it

In Defense of Uniform Convergence: Generalization via derandomization with an application to interpolating predictors
We propose to study the generalization error of a learned predictor ĥ in...
read it

InformationTheoretic Generalization Bounds for SGLD via DataDependent Estimates
In this work, we improve upon the stepwise analysis of noisy iterative l...
read it

Fastrate PACBayes Generalization Bounds via Shifted Rademacher Processes
The developments of Rademacher complexity and PACBayesian theory have b...
read it

Blackbox constructions for exchangeable sequences of random multisets
We develop constructions for exchangeable sequences of point processes t...
read it

NUQSGD: Improved Communication Efficiency for Dataparallel SGD via Nonuniform Quantization
As the size and complexity of models and datasets grow, so does the need...
read it

The Lottery Ticket Hypothesis at Scale
Recent work on the "lottery ticket hypothesis" proposes that randomlyin...
read it

The BetaBernoulli process and algebraic effects
In this paper we analyze the BetaBernoulli process from Bayesian nonpar...
read it

Datadependent PACBayes priors via differential privacy
The Probably Approximately Correct (PAC) Bayes framework (McAllester, 19...
read it

On the computability of graphons
We investigate the relative computability of exchangeable binary relatio...
read it

EntropySGD optimizes the prior of a PACBayes bound: Datadependent PACBayes priors via differential privacy
We show that EntropySGD (Chaudhari et al., 2016), when viewed as a lear...
read it

Exchangeable modelling of relational data: checking sparsity, traintest splitting, and sparse exchangeable Poisson matrix factorization
A variety of machine learning taskse.g., matrix factorization, topic ...
read it

An estimator for the tailindex of graphex processes
Sparse exchangeable graphs resolve some pathologies in traditional rando...
read it

A study of the effect of JPG compression on adversarial images
Neural network image classifiers are known to be vulnerable to adversari...
read it

A characterization of productform exchangeable feature probability functions
We characterize the class of exchangeable feature allocations assigning ...
read it

The Mondrian Kernel
We introduce the Mondrian kernel, a fast random feature approximation to...
read it

Measuring the reliability of MCMC inference with bidirectional Monte Carlo
Markov chain Monte Carlo (MCMC) is one of the main workhorses of probabi...
read it

Gibbstype Indian buffet processes
We investigate a class of feature allocation models that generalize the ...
read it

Neural Network Matrix Factorization
Data often comes in the form of an array or matrix. Matrix factorization...
read it

Mondrian Forests for LargeScale Regression when Uncertainty Matters
Many realworld regression problems demand a measure of the uncertainty ...
read it

Training generative neural networks via Maximum Mean Discrepancy optimization
We consider training a deep neural network to generate samples from an u...
read it

Particle Gibbs for Bayesian Additive Regression Trees
Additive regression trees are flexible nonparametric models and popular...
read it

The continuumofurns scheme, generalized beta and Indian buffet processes, and hierarchies thereof
We describe the combinatorial stochastic process underlying a sequence o...
read it

The combinatorial structure of beta negative binomial processes
We characterize the combinatorial structure of conditionallyi.i.d. sequ...
read it

Bayesian Models of Graphs, Arrays and Other Exchangeable Random Structures
The natural habitat of most Bayesian methods is data represented by exch...
read it

Topdown particle filtering for Bayesian decision trees
Decision tree learning is a popular approach for classification and regr...
read it

Towards commonsense reasoning via conditional simulation: legacies of Turing in Artificial Intelligence
The problem of replicating the flexibility of human commonsense reasoni...
read it

Church: a language for generative models
We introduce Church, a universal language for describing stochastic gene...
read it

Computable de Finetti measures
We prove a computable version of de Finetti's theorem on exchangeable se...
read it