130 citations · 209 across the 59 of their papers we have counts for
11 papers · 1 filter
On Learning-Curve Monotonicity for Maximum Likelihood Estimators
Mark Sellke, Steven Yin
The property of learning-curve monotonicity, highlighted in a recent series of work by Loog, Mey and Viering, describes algorithms which only improve in average performance given m…
Exponentially Slow Mixing of the Low Temperature SK Model
Mark Sellke
We give a short proof that low-temperature dynamics for the Sherrington-Kirkpatrick model have mixing time exponential in the system size, based on the recently proved existence of…
Early science acceleration experiments with GPT-5
Sébastien Bubeck, Christian Coester, Ronen Eldan +11
AI models like GPT-5 are an increasingly valuable tool for scientists, but many remain unaware of the capabilities of frontier AI. We present a collection of short case studies in…
Sub-diffusive regimes for long range self-interacting path measures
Volker Betz, Tobias Schmidt, Mark Sellke
We study Brownian motion perturbed by a long range self-interaction. We provide variance bounds in terms of the spatial interaction strength and the order of time decay.
Universality of Cutoff for Riffle Shuffling
Mark Sellke, Jialu Shi, Jiamin Wang
A Gilbert-Shannon-Reeds (GSR) shuffle is performed on a deck of cards by cutting the top cards and interleaving the two resulting piles uniformly at random.…
On the Discontinuous Breaking of Replica Symmetry and Shattering in Mean-Field Spin Glasses
Antonio Auffinger, Ahmed El Alaoui, Mark Sellke
We show that in mean-field spin glasses, a discontinuous breaking of replica symmetry at the critical inverse temperature implies the existence of an intermediate shattered p…
Geometry Meets Incentives: Sample-Efficient Incentivized Exploration with Linear Contexts
Benjamin Schiffer, Mark Sellke
In the incentivized exploration model, a principal aims to explore and learn over time by interacting with a sequence of self-interested agents. It has been recently understood tha…
Strong Low Degree Hardness for the Number Partitioning Problem
Rushil Mallarapu, Mark Sellke
In the number partitioning problem (NPP) one aims to partition a given set of real numbers into two subsets with approximately equal sum. The NPP is a well-studied optimization…
Tight Low Degree Hardness for Optimizing Pure Spherical Spin Glasses
Mark Sellke
We prove constant degree polynomial algorithms cannot optimize pure spherical -spin Hamiltonians beyond the algorithmic threshold . The pr…
Nonparametric MLE for Gaussian Location Mixtures: Certified Computation and Generic Behavior
Yury Polyanskiy, Mark Sellke
We study the nonparametric maximum likelihood estimator for Gaussian location mixtures in one dimension. It has been known since (Lindsay, 1983) that given an -point…
Strong Low Degree Hardness for Stable Local Optima in Spin Glasses
Brice Huang, Mark Sellke
It is a folklore belief in the theory of spin glasses and disordered systems that out-of-equilibrium dynamics fail to find stable local optima exhibiting e.g. local strict convexit…