Search Results for author: Anna Mészáros

Found 6 papers, 2 papers with code

Understanding LLMs Requires More Than Statistical Generalization

no code implementations3 May 2024 Patrik Reizinger, Szilvia Ujváry, Anna Mészáros, Anna Kerekes, Wieland Brendel, Ferenc Huszár

The last decade has seen blossoming research in deep learning theory attempting to answer, "Why does deep learning generalize?"

In-Context Learning Learning Theory

Robust Multi-Modal Density Estimation

no code implementations19 Jan 2024 Anna Mészáros, Julian F. Schumann, Javier Alonso-Mora, Arkady Zgonnikov, Jens Kober

We compared our approach to state-of-the-art methods for density estimation as well as ablations of ROME, showing that it not only outperforms established methods but is also more robust to a variety of distributions.

Density Estimation

Rethinking Sharpness-Aware Minimization as Variational Inference

no code implementations19 Oct 2022 Szilvia Ujváry, Zsigmond Telek, Anna Kerekes, Anna Mészáros, Ferenc Huszár

Sharpness-aware minimization (SAM) aims to improve the generalisation of gradient-based learning by seeking out flat minima.

Variational Inference

Depth Without the Magic: Inductive Bias of Natural Gradient Descent

no code implementations22 Nov 2021 Anna Kerekes, Anna Mészáros, Ferenc Huszár

In gradient descent, changing how we parametrize the model can lead to drastically different optimization trajectories, giving rise to a surprising range of meaningful inductive biases: identifying sparse classifiers or reconstructing low-rank matrices without explicit regularization.

Inductive Bias

Learning to Pick at Non-Zero-Velocity from Interactive Demonstrations

1 code implementation9 Oct 2021 Anna Mészáros, Giovanni Franzese, Jens Kober

This work investigates how the intricate task of a continuous pick & place (P&P) motion may be learned from humans based on demonstrations and corrections.

Gaussian Processes

ILoSA: Interactive Learning of Stiffness and Attractors

1 code implementation4 Mar 2021 Giovanni Franzese, Anna Mészáros, Luka Peternel, Jens Kober

Teaching robots how to apply forces according to our preferences is still an open challenge that has to be tackled from multiple engineering perspectives.

Gaussian Processes

Cannot find the paper you are looking for? You can Submit a new open access paper.