Author name cluster

Daniel Beck

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

4 papers

2 author rows

NeurIPS Conference 2025 Conference Paper

Zero-Shot Performance Prediction for Probabilistic Scaling Laws

Viktoria Schram
Markus Hiller
Daniel Beck
Trevor Cohn

The prediction of learning curves for Natural Language Processing (NLP) models enables informed decision-making to meet specific performance objectives, while reducing computational overhead and lowering the costs associated with dataset acquisition and curation. In this work, we formulate the prediction task as a multitask learning problem, where each task’s data is modelled as being organized within a two-layer hierarchy. To model the shared information and dependencies across tasks and hierarchical levels, we employ latent variable multi-output Gaussian Processes, enabling to account for task correlations and supporting zero-shot prediction of learning curves (LCs). We demonstrate that this approach facilitates the development of probabilistic scaling laws at lower costs. Applying an active learning strategy, LCs can be queried to reduce predictive uncertainty and provide predictions close to ground truth scaling laws. We validate our framework on three small-scale NLP datasets with up to $30$ LCs. These are obtained from nanoGPT models, from bilingual translation using mBART and Transformer models, and from multilingual translation using M2M100 models of varying sizes.

PDF Details

YNIMG Journal 2023 Journal Article

Disease progression modelling of Alzheimer’s disease using probabilistic principal components analysis

Martin Saint-Jalmes
Victor Fedyashov
Daniel Beck
Timothy Baldwin
Noel G. Faux
Pierrick Bourgeat
Jurgen Fripp
Colin L. Masters

The recent biological redefinition of Alzheimer's Disease (AD) has spurred the development of statistical models that relate changes in biomarkers with neurodegeneration and worsening condition linked to AD. The ability to measure such changes may facilitate earlier diagnoses for affected individuals and help in monitoring the evolution of their condition. Amongst such statistical tools, disease progression models (DPMs) are quantitative, data-driven methods that specifically attempt to describe the temporal dynamics of biomarkers relevant to AD. Due to the heterogeneous nature of this disease, with patients of similar age experiencing different AD-related changes, a challenge facing longitudinal mixed-effects-based DPMs is the estimation of patient-realigning time-shifts. These time-shifts are indispensable for meaningful biomarker modelling, but may impact fitting time or vary with missing data in jointly estimated models. In this work, we estimate an individual's progression through Alzheimer's disease by combining multiple biomarkers into a single value using a probabilistic formulation of principal components analysis. Our results show that this variable, which summarises AD through observable biomarkers, is remarkably similar to jointly estimated time-shifts when we compute our scores for the baseline visit, on cross-sectional data from the Alzheimer's Disease Neuroimaging Initiative (ADNI). Reproducing the expected properties of clinical datasets, we confirm that estimated scores are robust to missing data or unavailable biomarkers. In addition to cross-sectional insights, we can model the latent variable as an individual progression score by repeating estimations at follow-up examinations and refining long-term estimates as more data is gathered, which would be ideal in a clinical setting. Finally, we verify that our score can be used as a pseudo-temporal scale instead of age to ignore some patient heterogeneity in cohort data and highlight the general trend in expected biomarker evolution in affected individuals.

Details DOI

NeurIPS Conference 2020 Conference Paper

BOSS: Bayesian Optimization over String Spaces

Henry Moss
David Leslie
Daniel Beck
Javier González
Paul Rayson

This article develops a Bayesian optimization (BO) method which acts directly over raw strings, proposing the first uses of string kernels and genetic algorithms within BO loops. Recent applications of BO over strings have been hindered by the need to map inputs into a smooth and unconstrained latent space. Learning this projection is computationally and data-intensive. Our approach instead builds a powerful Gaussian process surrogate model based on string kernels, naturally supporting variable length inputs, and performs efficient acquisition function maximization for spaces with syntactic constraints. Experiments demonstrate considerably improved optimization over existing approaches across a broad range of constraints, including the popular setting where syntax is governed by a context-free grammar.

PDF Details

ECAI Conference 2012 Conference Paper

Representing Value Functions with Recurrent Binary Decision Diagrams

Daniel Beck
Gerhard Lakemeyer

The agent programming language Golog features nondeterministic constructs such as nondeterministic branching. Given an optimization theory the nondeterminism can be resolved optimally. There are techniques that allow to derive an abstract first-order description of a value function which is valid across all possible domain instances. The size of the domain may be unknown or even infinite. A finite horizon is assumed, though. That is, although the value function makes no assumptions about the size of the domain, the plans generated on the basis of the value functions are restricted to a certain length. In this paper we present a solution for this dilemma for a specific class of programs. In particular, we present a solution that allows to compute a representation of the value function for non-nested loops without requiring any restrictions on the number of loop iterations. A pleasing side effect is that our new representation of the value function is usually smaller than the representations for fixed horizons.

Details