We present a three-tier progression of Hidden Markov Models: maximum-likelihood (Baum-Welch), variational Bayesian (VBEM), and a neural variational extension (Neural VBEM), that model each customer's transaction history as a trajectory through a small number of latent behavioural regimes, one of which is empirically id...
Joseph Uririoghene Obukofe, A. O'Hare, Chioma Sandra Dike· 0 citations
It is shown that a simple Follow-the-Perturbed-Leader algorithm with Gaussian perturbation for each observed context achieves the optimal $\widetilde O(\sqrt{T\log N})$ expected regret for a class of $N$ experts, while requiring one optimization-oracle call per round and no explicit enumeration of the class.
Understanding why predictors can generalize despite interpolating noisy training data is a central puzzle in machine learning. Most work on such "benign overfitting" studies minimum-2-norm linear regression, reflecting the inductive bias of gradient descent. However, modern optimizers such as Adam and Muon use non-Eucl...
We introduce RareTrap, a framework for estimating the probability of severe behaviors in black box large language models (LLMs). A key challenge for probability estimation is defining a tractable distribution over the input space. To accomplish that, RareTrap uses a surrogate LLM and constructs a geometry-aware mapping...
Elsayed Eshra, Ali Al-Lawati, Dongwon Lee et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Time series forecasting requires extrapolating the dynamics of an observed process beyond the last available measurement. Yet recurrent forecasting models typically treat observations as inputs that directly control their latent dynamics. It leads to a regime change when these observations become unavailable at predict...
Alexis-Raja Brachet, Guillaume Clavier-Frémond, Abdelhakim Ziani et al.· 0 citations
SLP-ProbHard is introduced, a cross-family, representation-centered framework for probabilistic hard-constrained learning when explicit structural parameterizations are available, and how feasible coordinates and maps affect stochastic dimension, dependence, calibration, expressiveness, and computation is studied.
Posterior sampling for reinforcement learning (PSRL) is one of the simplest and most effective exploration methods, but a basic question has remained open: does unmodified PSRL achieve minimax regret without structural assumptions on the prior? We answer yes. Exact vanilla PSRL is minimax optimal in leading-order Bayes...
Gaussian process stochastic differential equations (GP-SDEs) provide a flexible Bayesian model for unknown continuous-time state dynamics with uncertainty quantification, but learning and inference from noisy and irregular observations remain computationally challenging. To address this issue, we propose GP-SDE Matchin...
Zhi-Di Lin, Yu-Hao Liu, Ying Li et al.· 0 citations
Low-rank matrix and tensor bandits exploit structured interactions but typically assume a known reward link. Recent single-index bandit methods accommodate unknown links without directly exploiting matrix or tensor rank. We address this gap by studying stochastic matrix and tensor bandits with an unknown shared Lipschi...
Inferring quantities of interest (QoI) from data is a central task in Science and Engineering. In such contexts, we often have access to both quantitative data and qualitative data. Quantitative data may be represented by noisy sensor measurements, simulation data, re-analysis data; qualitative data may be in the form...
Pengyu Zhang, Mark Girolami, Arnaud Vadeboncoeur· 0 citations
We study distributionally robust reinforcement learning (DR-RL) in the average-reward setting under weak communication. Our main result provides finite-sample guarantees for estimating the robust optimal average reward and learning a near-optimal policy, covering both SA-rectangular and S-rectangular structures with di...
This work introduces a symbolic distillation pipeline that converts trained neural likelihoods into explicit, interpretable expressions optimized for efficient parameter estimation, and uses a recovery-directed objective to guide symbolic regression toward expressions that preserve parameter-recovery accuracy.
Jennifer Neville did not want to go into computer science—but that’s exactly where she landed. Neville discusses the starts and stops that led to her professional sweet spot and her work identifying “surprising failures” making it hard for AI to handle complexity. The post What AI gets wrong and what failure teaches us appeared first on Microsoft Research.
