arXiv subjects

Bernhard Schölkopf

Publications and source records attributed to Bernhard Schölkopf.

At least 127 records · Page 7Linked to original sources

arXiv2025

Multi-Armed Bandits and Quantum Channel Oracles

Multi-armed bandits are one of the theoretical pillars of reinforcement learning. Recently, the investigation of quantum algorithms for multi-armed bandit problems was started, and it was found that a quadratic speed-up (in query complexity) is possible when the arms and the randomness of the rewards of the arms can be queried in superposition. Here we introduce further bandit models where we only have limited access to the randomness of the rewards, but we can still query the arms in superposition. We show that then the query complexity is the same as for classical algorithms. This generalizes the prior result that no speed-up is possible for unstructured search when the oracle has positive failure probability.

quant-ph↗

arXiv2025

DARS: Dynamic Action Re-Sampling to Enhance Coding Agent Performance by Adaptive Tree Traversal

Large Language Models (LLMs) have revolutionized various domains, including natural language processing, data analysis, and software development, by enabling automation. In software engineering, LLM-powered coding agents have garnered significant attention due to their potential to automate complex development tasks, assist in debugging, and enhance productivity. However, existing approaches often struggle with sub-optimal decision-making, requiring either extensive manual intervention or inefficient compute scaling strategies. To improve coding agent performance, we present Dynamic Action Re-Sampling (DARS), a novel inference time compute scaling approach for coding agents, that is faster and more effective at recovering from sub-optimal decisions compared to baselines. While traditional agents either follow linear trajectories or rely on random sampling for scaling compute, our approach DARS works by branching out a trajectory at certain key decision points by taking an alternative action given the history of the trajectory and execution feedback of the previous attempt from that point. We evaluate our approach on SWE-Bench Lite benchmark, demonstrating that this scaling strategy achieves a pass@k score of 55% with Claude 3.5 Sonnet V2. Our framework achieves a pass@1 rate of 47%, outperforming state-of-the-art (SOTA) open-source frameworks.

cs.CL↗

arXiv2025

Standardizing Structural Causal Models

Synthetic datasets generated by structural causal models (SCMs) are commonly used for benchmarking causal structure learning algorithms. However, the variances and pairwise correlations in SCM data tend to increase along the causal ordering. Several popular algorithms exploit these artifacts, possibly leading to conclusions that do not generalize to real-world settings. Existing metrics like $\operatorname{Var}$-sortability and $\operatorname{R^2}$-sortability quantify these patterns, but they do not provide tools to remedy them. To address this, we propose internally-standardized structural causal models (iSCMs), a modification of SCMs that introduces a standardization operation at each variable during the generative process. By construction, iSCMs are not $\operatorname{Var}$-sortable. We also find empirical evidence that they are mostly not $\operatorname{R^2}$-sortable for commonly-used graph families. Moreover, contrary to the post-hoc standardization of data generated by standard SCMs, we prove that linear iSCMs are less identifiable from prior knowledge on the weights and do not collapse to deterministic relationships in large systems, which may make iSCMs a useful model in causal inference beyond the benchmarking problem studied here. Our code is publicly available at: https://github.com/werkaaa/iscm.

cs.LG↗

arXiv2025

Preference Elicitation for Offline Reinforcement Learning

Applying reinforcement learning (RL) to real-world problems is often made challenging by the inability to interact with the environment and the difficulty of designing reward functions. Offline RL addresses the first challenge by considering access to an offline dataset of environment interactions labeled by the reward function. In contrast, Preference-based RL does not assume access to the reward function and learns it from preferences, but typically requires an online interaction with the environment. We bridge the gap between these frameworks by exploring efficient methods for acquiring preference feedback in a fully offline setup. We propose Sim-OPRL, an offline preference-based reinforcement learning algorithm, which leverages a learned environment model to elicit preference feedback on simulated rollouts. Drawing on insights from both the offline RL and the preference-based RL literature, our algorithm employs a pessimistic approach for out-of-distribution data, and an optimistic approach for acquiring informative preferences about the optimal policy. We provide theoretical guarantees regarding the sample complexity of our approach, dependent on how well the offline data covers the optimal policy. Finally, we demonstrate the empirical performance of Sim-OPRL in various environments.

cs.LG↗

arXiv2025

Conformal Generative Modeling with Improved Sample Efficiency through Sequential Greedy Filtering

Generative models lack rigorous statistical guarantees for their outputs and are therefore unreliable in safety-critical applications. In this work, we propose Sequential Conformal Prediction for Generative Models (SCOPE-Gen), a sequential conformal prediction method producing prediction sets that satisfy a rigorous statistical guarantee called conformal admissibility control. This guarantee states that with high probability, the prediction sets contain at least one admissible (or valid) example. To this end, our method first samples an initial set of i.i.d. examples from a black box generative model. Then, this set is iteratively pruned via so-called greedy filters. As a consequence of the iterative generation procedure, admissibility of the final prediction set factorizes as a Markov chain. This factorization is crucial, because it allows to control each factor separately, using conformal prediction. In comparison to prior work, our method demonstrates a large reduction in the number of admissibility evaluations during calibration. This reduction is important in safety-critical applications, where these evaluations must be conducted manually by domain experts and are therefore costly and time consuming. We highlight the advantages of our method in terms of admissibility evaluations and cardinality of the prediction sets through experiments in natural language generation and molecular graph extension tasks.

cs.LG↗

arXiv2025

Verbalized Machine Learning: Revisiting Machine Learning with Language Models

Motivated by the progress made by large language models (LLMs), we introduce the framework of verbalized machine learning (VML). In contrast to conventional machine learning (ML) models that are typically optimized over a continuous parameter space, VML constrains the parameter space to be human-interpretable natural language. Such a constraint leads to a new perspective of function approximation, where an LLM with a text prompt can be viewed as a function parameterized by the text prompt. Guided by this perspective, we revisit classical ML problems, such as regression and classification, and find that these problems can be solved by an LLM-parameterized learner and optimizer. The major advantages of VML include (1) easy encoding of inductive bias: prior knowledge about the problem and hypothesis class can be encoded in natural language and fed into the LLM-parameterized learner; (2) automatic model class selection: the optimizer can automatically select a model class based on data and verbalized prior knowledge, and it can update the model class during training; and (3) interpretable learner updates: the LLM-parameterized optimizer can provide explanations for why an update is performed. We empirically verify the effectiveness of VML, and hope that VML can serve as a stepping stone to stronger interpretability.

cs.LG↗

arXiv2025

MathGAP: Out-of-Distribution Evaluation on Problems with Arbitrarily Complex Proofs

Large language models (LLMs) can solve arithmetic word problems with high accuracy, but little is known about how well they generalize to more complex problems. This is difficult to study, as (i) much of the available evaluation data has already been seen by the most capable models during training, and (ii) existing benchmarks do not capture how problem proofs may be arbitrarily complex in various ways. In this paper, we present a data-generation framework for evaluating LLMs on problems with arbitrarily complex arithmetic proofs, called MathGAP. MathGAP generates problem statements and chain-of-thought reasoning traces according to specifications about their arithmetic proof structure, enabling systematic studies on easy-to-hard generalization with respect to complexity of proof trees. Using MathGAP, we find that LLMs show a significant decrease in performance as proofs get deeper and wider. This effect is more pronounced in complex, nonlinear proof structures, which are challenging even for the most capable models. The models are also sensitive to simple changes in sentence ordering. However, they remain capable of solving some complex problems, suggesting that reasoning generalization is noisy.

cs.LG↗

arXiv2025

From Pixels to Components: Eigenvector Masking for Visual Representation Learning

Predicting masked from visible parts of an image is a powerful self-supervised approach for visual representation learning. However, the common practice of masking random patches of pixels exhibits certain failure modes, which can prevent learning meaningful high-level features, as required for downstream tasks. We propose an alternative masking strategy that operates on a suitable transformation of the data rather than on the raw pixels. Specifically, we perform principal component analysis and then randomly mask a subset of components, which accounts for a fixed ratio of the data variance. The learning task then amounts to reconstructing the masked components from the visible ones. Compared to local patches of pixels, the principal components of images carry more global information. We thus posit that predicting masked from visible components involves more high-level features, allowing our masking strategy to extract more useful representations. This is corroborated by our empirical findings which demonstrate improved image classification performance for component over pixel masking. Our method thus constitutes a simple and robust data-driven alternative to traditional masked image modeling approaches.

cs.LG↗

arXiv2025

Identifiable Exchangeable Mechanisms for Causal Structure and Representation Learning

Identifying latent representations or causal structures is important for good generalization and downstream task performance. However, both fields have been developed rather independently. We observe that several methods in both representation and causal structure learning rely on the same data-generating process (DGP), namely, exchangeable but not i.i.d. (independent and identically distributed) data. We provide a unified framework, termed Identifiable Exchangeable Mechanisms (IEM), for representation and structure learning under the lens of exchangeability. IEM provides new insights that let us relax the necessary conditions for causal structure identification in exchangeable non--i.i.d. data. We also demonstrate the existence of a duality condition in identifiable representation learning, leading to new identifiability results. We hope this work will pave the way for further research in causal representation learning.

stat.ML↗

arXiv2025

Causality can systematically address the monsters under the bench(marks)

Effective and reliable evaluation is essential for advancing empirical machine learning. However, the increasing accessibility of generalist models and the progress towards ever more complex, high-level tasks make systematic evaluation more challenging. Benchmarks are plagued by various biases, artifacts, or leakage, while models may behave unreliably due to poorly explored failure modes. Haphazard treatments and inconsistent formulations of such "monsters" can contribute to a duplication of efforts, a lack of trust in results, and unsupported inferences. In this position paper, we argue causality offers an ideal framework to systematically address these challenges. By making causal assumptions in an approach explicit, we can faithfully model phenomena, formulate testable hypotheses with explanatory power, and leverage principled tools for analysis. To make causal model design more accessible, we identify several useful Common Abstract Topologies (CATs) in causal graphs which help gain insight into the reasoning abilities in large language models. Through a series of case studies, we demonstrate how the precise yet pragmatic language of causality clarifies the strengths and limitations of a method and inspires new approaches for systematic progress.

cs.LG↗

arXiv2025

Use the 4S (Signal-Safe Speckle Subtraction): Explainable Machine Learning reveals the Giant Exoplanet AF Lep b in High-Contrast Imaging Data from 2011

The main challenge of exoplanet high-contrast imaging (HCI) is to separate the signal of exoplanets from their host stars, which are many orders of magnitude brighter. HCI for ground-based observations is further exacerbated by speckle noise originating from perturbations in Earth's atmosphere and imperfections in the telescope optics. Various data post-processing techniques are used to remove this speckle noise and reveal the faint planet signal. Often, however, a significant part of the planet signal is accidentally subtracted together with the noise. In the present work, we use explainable machine learning to investigate the reason for the loss of the planet signal for one of the most used post-processing methods: principal component analysis (PCA). We find that PCA learns the shape of the telescope point spread function for high numbers of PCA components. This representation of the noise captures not only the speckle noise but also the characteristic shape of the planet signal. Building on these insights, we develop a new post-processing method (4S) that constrains the noise model to minimize this signal loss. We apply our model to 11 archival HCI datasets from the VLT-NACO instrument in the L'-band and find that our model consistently outperforms PCA. The improvement is largest at close separations to the star ($\leq 4 λ/D$) providing up to 1.5 magnitudes deeper contrast. This enhancement enables us to detect the exoplanet AF Lep b in data from 2011, 11 years before its subsequent discovery. We present updated orbital parameters for this object.

astro-ph.EP↗

arXiv2025

International AI Safety Report

The first International AI Safety Report comprehensively synthesizes the current evidence on the capabilities, risks, and safety of advanced AI systems. The report was mandated by the nations attending the AI Safety Summit in Bletchley, UK. Thirty nations, the UN, the OECD, and the EU each nominated a representative to the report's Expert Advisory Panel. A total of 100 AI experts contributed, representing diverse perspectives and disciplines. Led by the report's Chair, these independent experts collectively had full discretion over the report's content.

cs.CY↗

arXiv2025

Causal vs. Anticausal merging of predictors

We study the differences arising from merging predictors in the causal and anticausal directions using the same data. In particular we study the asymmetries that arise in a simple model where we merge the predictors using one binary variable as target and two continuous variables as predictors. We use Causal Maximum Entropy (CMAXENT) as inductive bias to merge the predictors, however, we expect similar differences to hold also when we use other merging methods that take into account asymmetries between cause and effect. We show that if we observe all bivariate distributions, the CMAXENT solution reduces to a logistic regression in the causal direction and Linear Discriminant Analysis (LDA) in the anticausal direction. Furthermore, we study how the decision boundaries of these two solutions differ whenever we observe only some of the bivariate distributions implications for Out-Of-Variable (OOV) generalisation.

cs.LG↗

arXiv2025

Multi-megabase scale genome interpretation with genetic language models

Understanding how molecular changes caused by genetic variation drive disease risk is crucial for deciphering disease mechanisms. However, interpreting genome sequences is challenging because of the vast size of the human genome, and because its consequences manifest across a wide range of cells, tissues and scales -- spanning from molecular to whole organism level. Here, we present Phenformer, a multi-scale genetic language model that learns to generate mechanistic hypotheses as to how differences in genome sequence lead to disease-relevant changes in expression across cell types and tissues directly from DNA sequences of up to 88 million base pairs. Using whole genome sequencing data from more than 150 000 individuals, we show that Phenformer generates mechanistic hypotheses about disease-relevant cell and tissue types that match literature better than existing state-of-the-art methods, while using only sequence data. Furthermore, disease risk predictors enriched by Phenformer show improved prediction performance and generalisation to diverse populations. Accurate multi-megabase scale interpretation of whole genomes without additional experimental data enables both a deeper understanding of molecular mechanisms involved in disease and improved disease risk prediction at the level of individuals.

q-bio.GN↗

arXiv2024

On Affine Homotopy between Language Encoders

Pre-trained language encoders -- functions that represent text as vectors -- are an integral component of many NLP tasks. We tackle a natural question in language encoder analysis: What does it mean for two encoders to be similar? We contend that a faithful measure of similarity needs to be \emph{intrinsic}, that is, task-independent, yet still be informative of \emph{extrinsic} similarity -- the performance on downstream tasks. It is common to consider two encoders similar if they are \emph{homotopic}, i.e., if they can be aligned through some transformation. In this spirit, we study the properties of \emph{affine} alignment of language encoders and its implications on extrinsic similarity. We find that while affine alignment is fundamentally an asymmetric notion of similarity, it is still informative of extrinsic similarity. We confirm this on datasets of natural language representations. Beyond providing useful bounds on extrinsic similarity, affine intrinsic similarity also allows us to begin uncovering the structure of the space of pre-trained encoders by defining an order over them.

cs.CL↗

arXiv2024

Learning Interpretable Concepts: Unifying Causal Representation Learning and Foundation Models

To build intelligent machine learning systems, there are two broad approaches. One approach is to build inherently interpretable models, as endeavored by the growing field of causal representation learning. The other approach is to build highly-performant foundation models and then invest efforts into understanding how they work. In this work, we relate these two approaches and study how to learn human-interpretable concepts from data. Weaving together ideas from both fields, we formally define a notion of concepts and show that they can be provably recovered from diverse data. Experiments on synthetic data and large language models show the utility of our unified approach.

cs.LG↗

arXiv2024

Cooperate or Collapse: Emergence of Sustainable Cooperation in a Society of LLM Agents

As AI systems pervade human life, ensuring that large language models (LLMs) make safe decisions remains a significant challenge. We introduce the Governance of the Commons Simulation (GovSim), a generative simulation platform designed to study strategic interactions and cooperative decision-making in LLMs. In GovSim, a society of AI agents must collectively balance exploiting a common resource with sustaining it for future use. This environment enables the study of how ethical considerations, strategic planning, and negotiation skills impact cooperative outcomes. We develop an LLM-based agent architecture and test it with the leading open and closed LLMs. We find that all but the most powerful LLM agents fail to achieve a sustainable equilibrium in GovSim, with the highest survival rate below 54%. Ablations reveal that successful multi-agent communication between agents is critical for achieving cooperation in these cases. Furthermore, our analyses show that the failure to achieve sustainable cooperation in most LLMs stems from their inability to formulate and analyze hypotheses about the long-term effects of their actions on the equilibrium of the group. Finally, we show that agents that leverage "Universalization"-based reasoning, a theory of moral thinking, are able to achieve significantly better sustainability. Taken together, GovSim enables us to study the mechanisms that underlie sustainable self-government with specificity and scale. We open source the full suite of our research results, including the simulation environment, agent prompts, and a comprehensive web interface.

cs.CL↗

arXiv2024

RP1M: A Large-Scale Motion Dataset for Piano Playing with Bi-Manual Dexterous Robot Hands

It has been a long-standing research goal to endow robot hands with human-level dexterity. Bi-manual robot piano playing constitutes a task that combines challenges from dynamic tasks, such as generating fast while precise motions, with slower but contact-rich manipulation problems. Although reinforcement learning based approaches have shown promising results in single-task performance, these methods struggle in a multi-song setting. Our work aims to close this gap and, thereby, enable imitation learning approaches for robot piano playing at scale. To this end, we introduce the Robot Piano 1 Million (RP1M) dataset, containing bi-manual robot piano playing motion data of more than one million trajectories. We formulate finger placements as an optimal transport problem, thus, enabling automatic annotation of vast amounts of unlabeled songs. Benchmarking existing imitation learning approaches shows that such approaches reach state-of-the-art robot piano playing performance by leveraging RP1M.

cs.RO↗