activity
20162026
most citedInformation Theoretic Properties of Markov Random Fields, and their Algorithmic Applications

24 citations · 101 across the 40 of their papers we have counts for

collaborators

42 papers

math.PR2026

Universality and sharp thresholds for ellipsoid fitting

Frederic Koehler, Youngtak Sohn

We establish a sharp phase transition for fitting random vectors by an ellipsoid. The random vectors have independent subgaussian coordinates with mean zero, variance one, and a co…

math.PR2026

Anticoncentration of the Permanent in Ginibre Ensembles

Frederic Koehler, Pui Kuen Leung

Let , put , and let be an matrix with i.i.d. standard -…

cs.LG2026

A Hierarchical Language Model with Predictable Scaling Laws and Provable Benefits of Reasoning

Jason Gaitonde, Frederic Koehler, Elchanan Mossel +2

We introduce a family of synthetic languages with hierarchical structure -- generated by a broadcast process on trees -- for which the role of context length and reasoning in autor…

cs.DS2026

Approximating the Permanent of a Random Matrix with Polynomially Small Mean: Zeros and Universality

Frederic Koehler, Pui Kuen Leung

We study algorithms for approximating the permanent of a random matrix when the entries are slightly biased away from zero. This question is motivated by the goal of understanding…

math.PR2024

Trickle-Down in Localization Schemes and Applications

Nima Anari, Frederic Koehler, Thuy-Duong Vuong

Trickle-down is a phenomenon in high-dimensional expanders with many important applications -- for example, it is a key ingredient in various constructions of high-dimensional expa…

stat.ML2024

Lasso with Latents: Efficient Estimation, Covariate Rescaling, and Computational-Statistical Gaps

Jonathan Kelner, Frederic Koehler, Raghu Meka +1

It is well-known that the statistical performance of Lasso can suffer significantly when the covariates of interest have strong correlations. In particular, the prediction error of…