1 citations · 1 across the 9 of their papers we have counts for
5 papers · 1 filter
Align & Invert: Solving Inverse Problems with Diffusion and Flow-based Models via Representation Alignment
Loukas Sfountouris, Giannis Daras, Paris Giampouras
Enforcing alignment between the internal representations of diffusion or flow-based generative models and those of pretrained self-supervised encoders has recently been shown to pr…
Distributionally Robust Causal Abstractions
Yorgos Felekis, Theodoros Damoulas, Paris Giampouras
Causal Abstraction (CA) theory provides a principled framework for relating causal models that describe the same system at different levels of granularity while ensuring interventi…
Rates of Convergence of Generalised Variational Inference Posteriors under Prior Misspecification
Terje Mildner, Paris Giampouras, Theodoros Damoulas
We prove rates of convergence and robustness to prior misspecification within a Generalised Variational Inference (GVI) framework with bounded divergences. This addresses a signifi…
DES-LOC: Desynced Low Communication Adaptive Optimizers for Training Foundation Models
Alex Iacob, Lorenzo Sani, Mher Safaryan +8
Scaling foundation model training with Distributed Data Parallel (DDP) methods is bandwidth-limited. Existing infrequent communication methods like Local SGD were designed to synch…
Federated Generalised Variational Inference: A Robust Probabilistic Federated Learning Framework
Terje Mildner, Oliver Hamelijnck, Paris Giampouras +1
We introduce FedGVI, a probabilistic Federated Learning (FL) framework that is robust to both prior and likelihood misspecification. FedGVI addresses limitations in both frequentis…