
Uniform Convergence of Interpolators: Gaussian Width, Norm Bounds, and Benign Overfitting
We consider interpolation learning in highdimensional linear regression...
read it

On the Power of Preconditioning in Sparse Linear Regression
Sparse linear regression is a fundamental problem in highdimensional st...
read it

Entropic Independence in HighDimensional Expanders: Modified LogSobolev Inequalities for Fractionally LogConcave Polynomials and the Ising Model
We introduce a notion called entropic independence for distributions μ d...
read it

ChowLiu++: Optimal PredictionCentric Learning of Tree Ising Models
We consider the problem of learning a treestructured Ising model from d...
read it

Online and DistributionFree Robustness: Regression and Contextual Bandits with Huber Contamination
In this work we revisit two classic highdimensional online learning pro...
read it

Representational aspects of depth and conditioning in normalizing flows
Normalizing flows are among the most popular paradigms in generative mod...
read it

From Boltzmann Machines to Neural Networks and Back Again
Graphical models are powerful tools for modeling highdimensional data, ...
read it

Classification Under Misspecification: Halfspaces, Generalized Linear Models, and Connections to Evolvability
In this paper we revisit some classic problems on classification under m...
read it

A Phase Transition in Arrow's Theorem
Arrow's Theorem concerns a fundamental problem in social choice theory: ...
read it

AccuracyMemory Tradeoffs and Phase Transitions in Belief Propagation
The analysis of Belief Propagation and other algorithms for the reconst...
read it

Fast Convergence of Belief Propagation to Global Optima: Beyond Correlation Decay
Belief propagation is a fundamental messagepassing algorithm for probab...
read it

Learning Some Popular Gaussian Graphical Models without Condition Number Bounds
Gaussian Graphical Models (GGMs) have wideranging applications in machi...
read it

How Many Subpopulations is Too Many? Exponential Lower Bounds for Inferring Population Histories
Reconstruction of population histories is a central problem in populatio...
read it

Meanfield approximation, convex hierarchies, and the optimality of correlation rounding: a unified perspective
The free energy is a key quantity of interest in Ising models, but unfor...
read it

Representational Power of ReLU Networks and Polynomial Kernels: Beyond WorstCase Analysis
There has been a large amount of interest, both in the past and particul...
read it

Learning Restricted Boltzmann Machines via Influence Maximization
Graphical models are a rich language for describing highdimensional dis...
read it

The Vertex Sample Complexity of Free Energy is Polynomial
We study the following question: given a massive Markov random field on ...
read it

The MeanField Approximation: Information Inequalities, Algorithms, and Complexity
The mean field approximation to the Ising model is a canonical variation...
read it

Approximating Partition Functions in Constant Time
We study approximations of the partition function of dense graphical mod...
read it

Provable Algorithms for Inference in Topic Models
Recently, there has been considerable progress on designing algorithms w...
read it
Frederic Koehler
is this you? claim profile