AIConfPaper
← Search

Bruno Kacper Mlodozeniec

9 accepted papers

2026

Completed Hyperparameter Transfer across Modules, Width, Depth, Batch and Duration

Bruno Kacper Mlodozeniec, Pierre Ablin, Louis Béthune, Dan Busbridge, Michal Klein, Jason Ramapuram +1
ICLR 2026poster

Hyperparameter tuning can dramatically impact training stability of large-scale models. Recent works on neural network parameterisations, such as μP, have shown that layer types and sizes should dictate how global hyperparameters should be rescaled in order to achieve efficient transfer across mode…

Cited by 0Source ↗Scholar ↗
2025

Distributional Training Data Attribution: What do Influence Functions Sample?

Bruno Kacper Mlodozeniec, Isaac Reid, Samuel Power, David Krueger, Murat A Erdogdu, Richard E. Turner +1
NeurIPS 2025spotlight

Randomness is an unavoidable part of training deep learning models, yet something that traditional training data attribution algorithms fail to rigorously account for. They ignore the fact that, due to stochasticity in the initialisation and batching, training on the same dataset can yield different…

Cited by 0Source ↗Scholar ↗
2025

Influence Functions for Scalable Data Attribution in Diffusion Models

Bruno Kacper Mlodozeniec, Runa Eschenhagen, Juhan Bae, Alexander Immer, David Krueger, Richard E. Turner
ICLR 2025oral

Diffusion models have led to significant advancements in generative modelling. Yet their widespread adoption poses challenges regarding data attribution and interpretability. In this paper, we aim to help address such challenges in diffusion models by extending influence functions. Influence functio…

Cited by 2Source ↗PDF ↗Scholar ↗
2025

Position: Probabilistic Modelling is Sufficient for Causal Inference

Bruno Kacper Mlodozeniec, David Krueger, Richard E. Turner
ICML 2025oral

Causal inference is a key research area in machine learning, yet confusion reigns over the tools needed to tackle it. There are prevalent claims in the machine learning literature that you need a bespoke causal framework or notation to answer causal questions. In this paper, we make it clear that yo…

Cited by 0Source ↗PDF ↗Scholar ↗
2024

A Generative Model of Symmetry Transformations

James Urquhart Allingham, Bruno Kacper Mlodozeniec, Shreyas Padhy, Javier Antoran, David Krueger, Richard E. Turner +2
NeurIPS 2024poster

Correctly capturing the symmetry transformations of data can lead to efficient models with strong generalization capabilities, though methods incorporating symmetries often require prior knowledge. While recent advancements have been made in learning those symmetries directly from the dataset, most…

Cited by 2Source ↗PDF ↗code ↗Scholar ↗
2024

Implicit meta-learning may lead language models to trust more reliable sources

Dmitrii Krasheninnikov, Egor Krasheninnikov, Bruno Kacper Mlodozeniec, Tegan Maharaj, David Krueger
ICML 2024poster

We demonstrate that large language models (LLMs) may learn indicators of document usefulness and modulate their updates accordingly. We introduce random strings ("tags") as indicators of usefulness in a synthetic fine-tuning dataset. Fine-tuning on this dataset leads to **implicit meta-learning (IML…

Cited by 8Source ↗PDF ↗code ↗Scholar ↗
2024

Improving Linear System Solvers for Hyperparameter Optimisation in Iterative Gaussian Processes

Jihao Andreas Lin, Shreyas Padhy, Bruno Kacper Mlodozeniec, Javier Antoran, José Miguel Hernández-Lobato
NeurIPS 2024poster

Scaling hyperparameter optimisation to very large datasets remains an open problem in the Gaussian process community. This paper focuses on iterative methods, which use linear system solvers, like conjugate gradients, alternating projections or stochastic gradient descent, to construct an estimate o…

Cited by 1Source ↗PDF ↗code ↗Scholar ↗
2023

Hyperparameter Optimization through Neural Network Partitioning

Bruno Kacper Mlodozeniec, Matthias Reisser, Christos Louizos
ICLR 2023poster

Well-tuned hyperparameters are crucial for obtaining good generalization behavior in neural networks. They can enforce appropriate inductive biases, regularize the model and improve performance --- especially in the presence of limited data. In this work, we propose a simple and efficient way for op…

Cited by 6Source ↗PDF ↗Scholar ↗
2023

Timewarp: Transferable Acceleration of Molecular Dynamics by Learning Time-Coarsened Dynamics

Leon Klein, Andrew Y. K. Foong, Tor Erlend Fjelde, Bruno Kacper Mlodozeniec, Marc Brockschmidt, Sebastian Nowozin +2
NeurIPS 2023spotlight

*Molecular dynamics* (MD) simulation is a widely used technique to simulate molecular systems, most commonly at the all-atom resolution where equations of motion are integrated with timesteps on the order of femtoseconds ($1\textrm{fs}=10^{-15}\textrm{s}$). MD is often used to compute equilibrium p…

Cited by 46Source ↗PDF ↗code ↗Scholar ↗