papers

Publications (19)

cs.LG2025

Position: An Empirically Grounded Identifiability Theory Will Accelerate Self-Supervised Learning Research

Patrik Reizinger, Randall Balestriero, David Klindt +1

Self-Supervised Learning (SSL) powers many current AI systems. As research interest and investment grow, the SSL design space continues to expand. The Platonic view of SSL, followi…

cs.LG2019

Attention-based Curiosity-driven Exploration in Deep Reinforcement Learning

Patrik Reizinger, Márton Szemenyei

Reinforcement Learning enables to train an agent via interaction with the environment. However, in the majority of real-world scenarios, the extrinsic feedback is sparse or not suf…

cs.LG2026

From Isolation to Entanglement: When Do Interpretability Methods Identify and Disentangle Known Concepts?

Aaron Mueller, Andrew Lee, Shruti Joshi +3

A goal of interpretability is to recover disentangled representations of latent concepts (features) from the activations of neural networks. The quality of features is typically ev…

cs.LG2026

Stabilizing Extrapolation in Looped Transformers via Learned Stochastic Stopping

Hsun-Yu Kuo, El Mahdi Chayti, Patrik Reizinger +2

Looped Transformers, which repeatedly apply a shared transformer block, are an architecturally natural fit for variable-length algorithmic tasks. Although they can exhibit strong l…

cs.LG2026

Who Guards the Guardians? The Challenges of Evaluating Identifiability of Learned Representations

Shruti Joshi, Théo Saulus, Wieland Brendel +3

Identifiability in representation learning is commonly evaluated using standard metrics (e.g., MCC, DCI, R^2) on synthetic benchmarks with known ground-truth factors. These metrics…

cs.LG2024

An Interventional Perspective on Identifiability in Gaussian LTI Systems with Independent Component Analysis

Goutham Rajendran, Patrik Reizinger, Wieland Brendel +1

We investigate the relationship between system identification and intervention design in dynamical systems. While previous research demonstrated how identifiable representation lea…

cs.LG2026

Causality is Key for Interpretability Claims to Generalise

Shruti Joshi, Aaron Mueller, David Klindt +3

Interpretability research on large language models (LLMs) has yielded important insights into model behaviour, yet recurring pitfalls persist: findings that do not generalise, and…

stat.ML2026

Estimating Treatment Effects with Independent Component Analysis

Patrik Reizinger, Lester Mackey, Wieland Brendel +1

Independent Component Analysis (ICA) uses a measure of non-Gaussianity to identify latent sources from data and estimate their mixing coefficients (Shimizu et al., 2006). Meanwhile…

cs.LG2025

Skill Learning via Policy Diversity Yields Identifiable Representations for Reinforcement Learning

Patrik Reizinger, Bálint Mucsányi, Siyuan Guo +3

Self-supervised feature learning and pretraining methods in reinforcement learning (RL) often rely on information-theoretic principles, termed mutual information skill learning (MI…

cs.LG2025

InfoNCE: Identifying the Gap Between Theory and Practice

Evgenia Rusak, Patrik Reizinger, Attila Juhos +3

Prior theory work on Contrastive Learning via the InfoNCE loss showed that, under certain assumptions, the learned representations recover the ground-truth latent factors. We argue…

stat.ML2024

Position: Understanding LLMs Requires More Than Statistical Generalization

Patrik Reizinger, Szilvia Ujváry, Anna Mészáros +3

The last decade has seen blossoming research in deep learning theory attempting to answer, "Why does deep learning generalize?" A powerful shift in perspective precipitated this pr…

cs.LG2025

Cross-Entropy Is All You Need To Invert the Data Generating Process

Patrik Reizinger, Alice Bizeul, Attila Juhos +4

Supervised learning has become a cornerstone of modern machine learning, yet a comprehensive theory explaining its effectiveness remains elusive. Empirical phenomena, such as neura…

cs.LG2025

From superposition to sparse codes: interpretable representations in neural networks

David Klindt, Charles O'Neill, Patrik Reizinger +2

Understanding how information is represented in neural networks is a fundamental challenge in both neuroscience and artificial intelligence. Despite their nonlinear architectures,…

stat.ML2025

Identifiable Exchangeable Mechanisms for Causal Structure and Representation Learning

Patrik Reizinger, Siyuan Guo, Ferenc Huszár +2

Identifying latent representations or causal structures is important for good generalization and downstream task performance. However, both fields have been developed rather indepe…

cs.CR2026

HALLMARK: Diagnosing Three Failure Modes in LLM Citation Verifiers

Patrik Reizinger, Wieland Brendel

Large language models (LLMs) now routinely draft literature reviews and assist with academic writing, which means a higher risk of fabricated references: GPTZero found 53 papers wi…

cs.LG2025

Out-of-distribution Tests Reveal Compositionality in Chess Transformers

Anna Mészáros, Patrik Reizinger, Ferenc Huszár

Chess is a canonical example of a task that requires rigorous reasoning and long-term planning. Modern decision Transformers - trained similarly to LLMs - are able to learn compete…

stat.ML2023

Embrace the Gap: VAEs Perform Independent Mechanism Analysis

Patrik Reizinger, Luigi Gresele, Jack Brady +6

Variational autoencoders (VAEs) are a popular framework for modeling complex data distributions; they can be efficiently trained via variational inference by maximizing the evidenc…

cs.LG2019

Stochastic Weight Matrix-based Regularization Methods for Deep Neural Networks

Patrik Reizinger, Bálint Gyires-Tóth

The aim of this paper is to introduce two widely applicable regularization methods based on the direct modification of weight matrices. The first method, Weight Reinitialization, u…

cs.CL2024

Rule Extrapolation in Language Models: A Study of Compositional Generalization on OOD Prompts

Anna Mészáros, Szilvia Ujváry, Wieland Brendel +2

LLMs show remarkable emergent abilities, such as inferring concepts from presumably out-of-distribution prompts, known as in-context learning. Though this success is often attribut…