collaborators

9 papers

stat.ML2026

Gaussian Invariant Markov Chain Monte Carlo

Michalis K. Titsias, Angelos Alexopoulos, Siran Liu +1

We develop sampling methods, which consist of Gaussian invariant versions of random walk Metropolis (RWM), Metropolis adjusted Langevin algorithm (MALA) and second order Hessian or…

cs.LG2026

Variational Learning for Insertion-based Generation

Yangtian Zhang, Zhe Wang, Arthur Gretton +4

Non-monotonic sequence generation methods, such as masked diffusion models, provide a flexible alternative to left-to-right autoregressive modeling by allowing tokens to be generat…

cs.CL2026

The Illusion of Stochasticity in LLMs

Xiangming Gu, Soham De, Michalis Titsias +3

In this work, we demonstrate that reliable stochastic sampling is a fundamental yet unfulfilled requirement for Large Language Models (LLMs) operating as agents. Agentic systems ar…

cs.LG2025

Personalized Federated Learning with Exact Stochastic Gradient Descent

Sotirios Nikoloutsopoulos, Iordanis Koutsopoulos, Michalis K. Titsias

We propose a Stochastic Gradient Descent (SGD)-type algorithm for Personalized Federated Learning which can be particularly attractive for mobile energy-limited regimes due to its…

cs.LG2025

Demystifying Diffusion Objectives: Reweighted Losses are Better Variational Bounds

Jiaxin Shi, Michalis K. Titsias

We derive a new theoretical interpretation of the reweighted losses that are widely used for training diffusion models. Our method is based on constructing a cascade of time-depend…

cs.LG2025

Learning-Order Autoregressive Models with Application to Molecular Graph Generation

Zhe Wang, Jiaxin Shi, Nicolas Heess +2

Autoregressive models (ARMs) have become the workhorse for sequence generation tasks, since many problems can be modeled as next-token prediction. While there appears to be a natur…