arXiv subjects

Andreas Kirsch

Publications and source records attributed to Andreas Kirsch.

At least 19 recordsLinked to original sources

arXiv2026

Large Language Model Selection with Limited Annotations

Choosing a Large Language Model (LLM) for a given task requires comparing many strong candidates, yet standard evaluation relies on costly annotations over fixed evaluation sets. To address this challenge, we develop SELECT-LLM, the first framework for active model selection of LLMs. SELECT-LLM aims to find a small set of queries whose annotations are most informative for identifying the best LLM for a given task. To this end, we introduce a query selection rule based on expected information gain, computed from pairwise similarities between candidate model outputs. Because this rule only uses generated model responses, SELECT-LLM can be applied across candidate models without assumptions about their architecture or access to model weights. This makes it suitable for both open-weight and black-box LLMs. We evaluate SELECT-LLM across 23 datasets, 156 evaluated models, diverse task families, and multiple text evaluation metrics. Across all experiments, SELECT-LLM improves over the strongest baseline in every setting, with annotation cost reductions up to 81.8% for best model selection and up to 84.78% for near-best model selection.

cs.CL↗

arXiv2026

Limiting absorption principle for time-harmonic acoustic and electromagnetic scattering of plane waves from a bi-periodic inhomogeneous layer

The Rayleigh expansion is widely used as a formal radiation condition in the analysis and numerical treatment of grating diffraction problems for incoming plane waves. However, the Rayleigh expansion does not always lead to uniqueness of open waveguide scattering problems, due to the existence of surface/guided waves (in other words, Bound States in the Continuum (BICs)) which exponentially decay in the direction perpendicular to the periodicity. In this paper we suppose that a bi-periodic inhomogeneous medium supports BICs at some real-valued incident wavenumber. Based on singular perturbation arguments, we justify the Limiting Absorption Principle (LAP) for both time-harmonic acoustic and electromagnetic scattering of plane waves from bi-periodic structures. Replacing the wavenumber $k$ with $k+i\epsilon$, we prove that the unique solution with $\epsilon>0$ converges to a solution of the original diffraction problem that additionally satisfies an orthogonal identity. This constraint condition together with the classical Rayleigh expansion leads to a sharp radiation condition to ensure uniqueness of time-harmonic scattering of plane waves by BIC-supporting bi-periodic materials.

math.AP↗

arXiv2025

Active Model Selection for Large Language Models

We introduce LLM SELECTOR, the first framework for active model selection of Large Language Models (LLMs). Unlike prior evaluation and benchmarking approaches that rely on fully annotated datasets, LLM SELECTOR efficiently identifies the best LLM with limited annotations. In particular, for any given task, LLM SELECTOR adaptively selects a small set of queries to annotate that are most informative about the best model for the task. To further reduce annotation cost, we leverage a judge-based oracle annotation model. Through extensive experiments on 6 benchmarks with 151 LLMs, we show that LLM SELECTOR reduces annotation costs by up to 59.62% when selecting the best and near-best LLM for the task.

cs.CL↗

arXiv2025

Evaluating the Robustness of Chinchilla Compute-Optimal Scaling

Hoffman et al (2022)'s Chinchilla paper introduced the principle of compute-optimal scaling, laying a foundation for future scaling of language models. In the years since, however, valid concerns about Chinchilla have been raised: wide confidence intervals, discrepancies between its three approaches, and incongruities with other scaling laws. This raises a critical question for the field: Can practitioners still rely on Chinchilla's prescriptions? Our work demonstrates the answer is yes. We begin by uncovering that the model parameters central to Chinchilla's analyses were ambiguous: three interpretations are possible, with relative differences between different interpretations of model parameters as high as 15.2%. We find that, perhaps surprisingly, which model parameters are used for the analyses do not meaningfully affect key results: the scaling law estimates and the compute-optimal tokens-to-parameter ratio. Indeed, under one interpretation, the tokens-to-parameter ratio becomes more constant with the target compute budget. We then ask how distorted the Chinchilla model parameters could have been without meaningfully affecting the key results. By deliberately perturbing model parameters in four structured ways, we find that key Chinchilla results are most sensitive to additive or systematic errors, which can alter the otherwise flat trend of the optimal tokens-to-parameter ratio, but overall, Chinchilla's key results withstand sizable perturbations. Altogether, our findings offer the field renewed confidence in Chinchilla as a durable guide for scaling language models.

cs.LG↗

arXiv2025

When three experiments are better than two: Avoiding intractable correlated aleatoric uncertainty by leveraging a novel bias--variance tradeoff

Real-world experimental scenarios are characterized by the presence of heteroskedastic aleatoric uncertainty, and this uncertainty can be correlated in batched settings. The bias--variance tradeoff can be used to write the expected mean squared error between a model distribution and a ground-truth random variable as the sum of an epistemic uncertainty term, the bias squared, and an aleatoric uncertainty term. We leverage this relationship to propose novel active learning strategies that directly reduce the bias between experimental rounds, considering model systems both with and without noise. Finally, we investigate methods to leverage historical data in a quadratic manner through the use of a novel cobias--covariance relationship, which naturally proposes a mechanism for batching through an eigendecomposition strategy. When our difference-based method leveraging the cobias--covariance relationship is utilized in a batched setting (with a quadratic estimator), we outperform a number of canonical methods including BALD and Least Confidence.

cs.LG↗

arXiv2024

All models are wrong, some are useful: Model Selection with Limited Labels

We introduce MODEL SELECTOR, a framework for label-efficient selection of pretrained classifiers. Given a pool of unlabeled target data, MODEL SELECTOR samples a small subset of highly informative examples for labeling, in order to efficiently identify the best pretrained model for deployment on this target dataset. Through extensive experiments, we demonstrate that MODEL SELECTOR drastically reduces the need for labeled data while consistently picking the best or near-best performing model. Across 18 model collections on 16 different datasets, comprising over 1,500 pretrained models, MODEL SELECTOR reduces the labeling cost by up to 94.15% to identify the best model compared to the cost of the strongest baseline. Our results further highlight the robustness of MODEL SELECTOR in model selection, as it reduces the labeling cost by up to 72.41% when selecting a near-best model, whose accuracy is only within 1% of the best model.

cs.LG↗

arXiv2024

(Implicit) Ensembles of Ensembles: Epistemic Uncertainty Collapse in Large Models

Epistemic uncertainty is crucial for safety-critical applications and data acquisition tasks. Yet, we find an important phenomenon in deep learning models: an epistemic uncertainty collapse as model complexity increases, challenging the assumption that larger models invariably offer better uncertainty quantification. We introduce implicit ensembling as a possible explanation for this phenomenon. To investigate this hypothesis, we provide theoretical analysis and experiments that demonstrate uncertainty collapse in explicit ensembles of ensembles and show experimental evidence of similar collapse in wider models across various architectures, from simple MLPs to state-of-the-art vision models including ResNets and Vision Transformers. We further develop implicit ensemble extraction techniques to decompose larger models into diverse sub-models, showing we can thus recover epistemic uncertainty. We explore the implications of these findings for uncertainty estimation.

cs.LG↗

arXiv2024

Turning Up the Heat: Min-p Sampling for Creative and Coherent LLM Outputs

Large Language Models (LLMs) generate text by sampling the next token from a probability distribution over the vocabulary at each decoding step. Popular sampling methods like top-p (nucleus sampling) often struggle to balance quality and diversity, especially at higher temperatures which lead to incoherent or repetitive outputs. We propose min-p sampling, a dynamic truncation method that adjusts the sampling threshold based on the model's confidence by using the top token's probability as a scaling factor. Our experiments on benchmarks including GPQA, GSM8K, and AlpacaEval Creative Writing show that min-p sampling improves both the quality and diversity of generated text across different model families (Mistral and Llama 3) and model sizes (1B to 123B parameters), especially at higher temperatures. Human evaluations further show a clear preference for min-p sampling, in both text quality and creativity. Min-p sampling has been adopted by popular open-source LLM frameworks, including Hugging Face Transformers, VLLM, and many others, highlighting its considerable impact on improving text generation quality.

cs.CL↗

arXiv2024

The Benefits and Risks of Transductive Approaches for AI Fairness

Recently, transductive learning methods, which leverage holdout sets during training, have gained popularity for their potential to improve speed, accuracy, and fairness in machine learning models. Despite this, the composition of the holdout set itself, particularly the balance of sensitive sub-groups, has been largely overlooked. Our experiments on CIFAR and CelebA datasets show that compositional changes in the holdout set can substantially influence fairness metrics. Imbalanced holdout sets exacerbate existing disparities, while balanced holdouts can mitigate issues introduced by imbalanced training data. These findings underline the necessity of constructing holdout sets that are both diverse and representative.

cs.LG↗

arXiv2024

CoLoR-Filter: Conditional Loss Reduction Filtering for Targeted Language Model Pre-training

Selecting high-quality data for pre-training is crucial in shaping the downstream task performance of language models. A major challenge lies in identifying this optimal subset, a problem generally considered intractable, thus necessitating scalable and effective heuristics. In this work, we propose a data selection method, CoLoR-Filter (Conditional Loss Reduction Filtering), which leverages an empirical Bayes-inspired approach to derive a simple and computationally efficient selection criterion based on the relative loss values of two auxiliary models. In addition to the modeling rationale, we evaluate CoLoR-Filter empirically on two language modeling tasks: (1) selecting data from C4 for domain adaptation to evaluation on Books and (2) selecting data from C4 for a suite of downstream multiple-choice question answering tasks. We demonstrate favorable scaling both as we subselect more aggressively and using small auxiliary models to select data for large target models. As one headline result, CoLoR-Filter data selected using a pair of 150m parameter auxiliary models can train a 1.2b parameter target model to match a 1.2b parameter model trained on 25b randomly selected tokens with 25x less data for Books and 11x less data for the downstream tasks. Code: https://github.com/davidbrandfonbrener/color-filter-olmo Filtered data: https://huggingface.co/datasets/davidbrandfonbrener/color-filtered-c4

cs.LG↗

arXiv2024

Direct and inverse time-harmonic scattering by Dirichlet periodic curves with local perturbations

This is a continuation of the authors' previous work (A. Kirsch, Math. Meth. Appl. Sci., 45 (2022): 5737-5773.) on well-posedness of time-harmonic scattering by locally perturbed periodic curves of Dirichlet kind. The scattering interface is supposed to be given by a non-self-intersecting Lipschitz curve. We study properties of the Green's function and prove new well-posedness results for scattering of plane waves at a propagative wave number. In such a case there exist guided waves to the unperturbed problem, which are also known as Bounded States in the Continuity (BICs) in physics. In this paper uniqueness of the forward scattering follows from an orthogonal constraint condition enforcing on the total field to the unperturbed scattering problem. This constraint condition, which is also valid under the Neumann boundary condition, is derived from the singular perturbation arguments and also from the approach of approximating a plane wave by point source waves. For the inverse problem of determining the defect, we prove several uniqueness results using a finite or infinite number of point source and plane waves, depending on whether a priori information on the size and height of the defect is available.

math.AP↗

arXiv2024

Time-harmonic scattering by locally perturbed periodic structures with Dirichlet and Neumann boundary conditions

The paper is concerned with well-posedness of TE and TM polarizations of time-harmonic electromagnetic scattering by perfectly conducting periodic surfaces and periodically arrayed obstacles with local perturbations. The classical Rayleigh Expansion radiation condition does not always lead to well-posedness of the Helmholtz equation even in unperturbed periodic structures. We propose two equivalent radiation conditions to characterize the radiating behavior of time-harmonic wave fields incited by a source term in an open waveguide under impenetrable boundary conditions. With these open waveguide radiation conditions, uniqueness and existence of time-harmonic scattering by incoming point source waves, plane waves and surface waves from locally perturbed periodic structures are established under either the Dirichlet or Neumann boundary condition. A DtN operator without using the Green's function is constructed for proving well-posedness of perturbed scattering problems.

math.AP↗

arXiv2024

Advancing Deep Active Learning & Data Subset Selection: Unifying Principles with Information-Theory Intuitions

At its core, this thesis aims to enhance the practicality of deep learning by improving the label and training efficiency of deep learning models. To this end, we investigate data subset selection techniques, specifically active learning and active sampling, grounded in information-theoretic principles. Active learning improves label efficiency, while active sampling enhances training efficiency. Supervised deep learning models often require extensive training with labeled data. Label acquisition can be expensive and time-consuming, and training large models is resource-intensive, hindering the adoption outside academic research and "big tech." Existing methods for data subset selection in deep learning often rely on heuristics or lack a principled information-theoretic foundation. In contrast, this thesis examines several objectives for data subset selection and their applications within deep learning, striving for a more principled approach inspired by information theory. We begin by disentangling epistemic and aleatoric uncertainty in single forward-pass deep neural networks, which provides helpful intuitions and insights into different forms of uncertainty and their relevance for data subset selection. We then propose and investigate various approaches for active learning and data subset selection in (Bayesian) deep learning. Finally, we relate various existing and proposed approaches to approximations of information quantities in weight or prediction space. Underpinning this work is a principled and practical notation for information-theoretic quantities that includes both random variables and observed outcomes. This thesis demonstrates the benefits of working from a unified perspective and highlights the potential impact of our contributions to the practical application of deep learning.

cs.LG↗

arXiv2024

The PML-Method for a Scattering Problem for a Local Perturbation of an Open Periodic Waveguide

The perfectly matched layers method is a well known truncation technique for its efficiency and convenience in numerical implementations of wave scattering problems in unbounded domains. In this paper, we study the convergence of the perfectly matched layers (PML) for wave scattering from a local perturbation of an open waveguide in the half space above the real line, where the refractive index is a function which is periodic along the axis of the waveguide and equals to one above a finite height. The problem is challenging due to the existence of guided waves, and a typical way to deal with the difficulty is to apply the limiting absorption principle. Based on the Floquet-Bloch transform and a curve deformation theory, the solution from the limiting absorption principle is rewritten as the integral of a coupled family of quasi-periodic problems with respect to the quasi-periodicity parameter on a particularly designed curve. By comparing the Dirichlet-to-Neumann maps on a straight line above the locally perturbed periodic layer, we finally show that the PML method converges exponentially with respect to the PML parameter. Finally, the numerical examples are shown to illustrate the theoretical results.

math.NA↗

arXiv2023

Prediction-Oriented Bayesian Active Learning

Information-theoretic approaches to active learning have traditionally focused on maximising the information gathered about the model parameters, most commonly by optimising the BALD score. We highlight that this can be suboptimal from the perspective of predictive performance. For example, BALD lacks a notion of an input distribution and so is prone to prioritise data of limited relevance. To address this we propose the expected predictive information gain (EPIG), an acquisition function that measures information gain in the space of predictions rather than parameters. We find that using EPIG leads to stronger predictive performance compared with BALD across a range of datasets and models, and thus provides an appealing drop-in replacement.

cs.LG↗

arXiv2023

Does "Deep Learning on a Data Diet" reproduce? Overall yes, but GraNd at Initialization does not

The paper 'Deep Learning on a Data Diet' by Paul et al. (2021) introduces two innovative metrics for pruning datasets during the training of neural networks. While we are able to replicate the results for the EL2N score at epoch 20, the same cannot be said for the GraNd score at initialization. The GraNd scores later in training provide useful pruning signals, however. The GraNd score at initialization calculates the average gradient norm of an input sample across multiple randomly initialized models before any training has taken place. Our analysis reveals a strong correlation between the GraNd score at initialization and the input norm of a sample, suggesting that the latter could have been a cheap new baseline for data pruning. Unfortunately, neither the GraNd score at initialization nor the input norm surpasses random pruning in performance. This contradicts one of the findings in Paul et al. (2021). We were unable to reproduce their CIFAR-10 results using both an updated version of the original JAX repository and in a newly implemented PyTorch codebase. An investigation of the underlying JAX/FLAX code from 2021 surfaced a bug in the checkpoint restoring code that was fixed in April 2021 (https://github.com/google/flax/commit/28fbd95500f4bf2f9924d2560062fa50e919b1a5).

cs.LG↗

arXiv2023

Black-Box Batch Active Learning for Regression

Batch active learning is a popular approach for efficiently training machine learning models on large, initially unlabelled datasets by repeatedly acquiring labels for batches of data points. However, many recent batch active learning methods are white-box approaches and are often limited to differentiable parametric models: they score unlabeled points using acquisition functions based on model embeddings or first- and second-order derivatives. In this paper, we propose black-box batch active learning for regression tasks as an extension of white-box approaches. Crucially, our method only relies on model predictions. This approach is compatible with a wide range of machine learning models, including regular and Bayesian deep learning models and non-differentiable models such as random forests. It is rooted in Bayesian principles and utilizes recent kernel-based approaches. This allows us to extend a wide range of existing state-of-the-art white-box batch active learning methods (BADGE, BAIT, LCMD) to black-box models. We demonstrate the effectiveness of our approach through extensive experimental evaluations on regression datasets, achieving surprisingly strong performance compared to white-box approaches for deep learning models.

cs.LG↗

arXiv2023

Speeding Up BatchBALD: A k-BALD Family of Approximations for Active Learning

Active learning is a powerful method for training machine learning models with limited labeled data. One commonly used technique for active learning is BatchBALD, which uses Bayesian neural networks to find the most informative points to label in a pool set. However, BatchBALD can be very slow to compute, especially for larger datasets. In this paper, we propose a new approximation, k-BALD, which uses k-wise mutual information terms to approximate BatchBALD, making it much less expensive to compute. Results on the MNIST dataset show that k-BALD is significantly faster than BatchBALD while maintaining similar performance. Additionally, we also propose a dynamic approach for choosing k based on the quality of the approximation, making it more efficient for larger datasets.

cs.LG↗