Benjamin Estermann

Last Name

Estermann

First Name

Benjamin

ORCID

0000-0001-8805-8298

Show all metadata

Search Results

Publications 1 - 10 of 13

Optimizing resource allocation: An active learning approach to iterative combinatorial auctions
Estermann, Benjamin; Kramer, Stefan; Wattenhofer, Roger; et al. (2025)
Theoretical Computer Science
In deep learning-based iterative combinatorial auctions (DL-ICA), bidders are not required to report valuations for all bundles upfront. Instead, DL-ICA iteratively requests bidders to report their values for specific bundles and determines item allocation using a winner determination problem, with bidder profiles modeled by neural networks. However, due to the limited number of reported bundles, DL-ICA may not always achieve optimal winner allocation, leading to reduced economic efficiency. In this work, we enhance the economic efficiency, specifically the social welfare, of DL-ICA by optimizing the underlying machine learning-based elicitation algorithm. We introduce two novel active learning-based initial sampling strategies: GALI and GALO. GALI ensures optimal coverage of the entire bundle space during sampling, while GALO identifies bundles with high diversity in bidders' estimated values as determined by the neural network. This approach extends the application of active learning beyond small pool sizes. We demonstrate how linear programs can be utilized for active learning to manage pool sizes exceeding 1030 samples. Our approach is theoretically validated and experimentally verified, showcasing significant improvements in performance.
Robust Disentanglement of a Few Factors at a Time using rPU-VAE
Estermann, Benjamin; Marks, Markus; Yanik, Mehmet F. (2021)
Advances in Neural Information Processing Systems 33
Disentanglement is at the forefront of unsupervised learning, as disentangled representations of data improve generalization, interpretability, and performance in downstream tasks. Current unsupervised approaches remain inapplicable for real-world datasets since they are highly variable in their performance and fail to reach levels of disentanglement of (semi-)supervised approaches. We introduce population-based training (PBT) for improving consistency in training variational autoencoders (VAEs) and demonstrate the validity of this approach in a supervised setting (PBT-VAE). We then use Unsupervised Disentanglement Ranking (UDR) as an unsupervised heuristic to score models in our PBT-VAE training and show how models trained this way tend to consistently disentangle only a subset of the generative factors. Building on top of this observation we introduce the recursive rPU-VAE approach. We train the model until convergence, remove the learned factors from the dataset and reiterate. In doing so, we can label subsets of the dataset with the learned factors and consecutively use these labels to train one model that fully disentangles the whole dataset. With this approach, we show striking improvement in state-of-the-art unsupervised disentanglement performance and robustness across multiple datasets and metrics.
Beyond Interpolation: Extrapolative Reasoning with Reinforcement Learning and Graph Neural Networks
Grillo, Niccolò; Toccaceli, Andrea; Mathys, Joël; et al. (2025)
The First Workshop on Neural Reasoning and Mathematical Discovery at AAAI'2025
Despite incredible progress, many neural architectures fail to properly generalize beyond their training distribution. As such, learning to reason in a correct and generalizable way is one of the current fundamental challenges in machine learning. In this respect, logic puzzles provide a great testbed, as we can fully understand and control the learning environment. Thus, they allow to evaluate performance on previously unseen, larger and more difficult puzzles that follow the same underlying rules. Since traditional approaches often struggle to represent such scalable logical structures, we propose to model these puzzles using a graph-based approach. Then, we investigate the key factors enabling the proposed models to learn generalizable solutions in a reinforcement learning setting. Our study focuses on the impact of the inductive bias of the architecture, different reward systems and the role of recurrent modeling in enabling sequential reasoning. Through extensive experiments, we demonstrate how these elements contribute to successful extrapolation on increasingly complex puzzles.These insights and frameworks offer a systematic way to design learning-based systems capable of generalizable reasoning beyond interpolation.
Deep Learning-Powered Iterative Combinatorial Auctions with Active Learning
Estermann, Benjamin; Kramer, Stefan; Wattenhofer, Roger; et al. (2023)
AAMAS '23: Proceedings of the 2023 International Conference on Autonomous Agents and Multiagent Systems
Deep learning-powered iterative combinatorial auctions (DL-ICA) are auctions that utilize machine learning techniques. Unlike traditional auctions, bidders in DL-ICA do not need to report the valuations for all bundles upfront. Instead, they report their value for certain bundles iteratively, and the allocation of the items is determined by solving a winner determination problem. During this process, the bidder profiles are modeled with neural networks. However, DL-ICA may not always achieve the optimal winner allocation due to the relatively low number of reported bundles, resulting in reduced economic efficiency. This paper proposes an algorithm that uses active learning for initial sampling strategies to improve the resulting economic efficiency (social welfare). The proposed algorithm outperforms previous studies in real-world combinatorial auction models across various domains while using fewer samples on average.
SUPClust: Active Learning at the Boundaries
Ono, Yuta; Aczel, Till; Estermann, Benjamin; et al. (2024)
5th Workshop on practical ML for limited/low resource settings
Active learning is a machine learning paradigm designed to optimize model performance in a setting where labeled data is expensive to acquire. In this work, we propose a novel active learning method called SUPClust that seeks to identify points at the decision boundary between classes. By targeting these points, SUPClust aims to gather information that is most informative for refining the model's prediction of complex decision regions. We demonstrate experimentally that labeling these points leads to strong model performance. This improvement is observed even in scenarios characterized by strong class imbalance.
Abstract Visual Reasoning Enabled by Language
Camposampiero, Giacomo; Houmard, Loic; Estermann, Benjamin; et al. (2023)
2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
While artificial intelligence (AI) models have achieved human or even superhuman performance in many well-defined applications, they still struggle to show signs of broad and flexible intelligence. The Abstraction and Reasoning Corpus (ARC), a visual intelligence benchmark introduced by François Chollet, aims to assess how close AI systems are to human-like cognitive abilities. Most current approaches rely on carefully handcrafted domain-specific program searches to brute-force solutions for the tasks present in ARC. In this work, we propose a general learning-based framework for solving ARC. It is centered on transforming tasks from the vision to the language domain. This composition of language and vision allows for pre-trained models to be leveraged at each stage, enabling a shift from handcrafted priors towards the learned priors of the models. While not yet beating state-of-the-art models on ARC, we demonstrate the potential of our approach, for instance, by solving some ARC tasks that have not been solved previously.
Bridging Diversity and Uncertainty in Active learning with Self-Supervised Pre-Training
Doucet, Paul; Estermann, Benjamin; Aczel, Till; et al. (2024)
5th Workshop on practical ML for limited/low resource settings
This study addresses the integration of diversity-based and uncertainty-based sampling strategies in active learning, particularly within the context of self-supervised pre-trained models. We introduce a straightforward heuristic called TCM that mitigates the cold start problem while maintaining strong performance across various data levels. By initially applying TypiClust for diversity sampling and subsequently transitioning to uncertainty sampling with Margin, our approach effectively combines the strengths of both strategies. Our experiments demonstrate that TCM consistently outperforms existing methods across various datasets in both low and high data regimes.
PUZZLES: A Benchmark for Neural Algorithmic Reasoning
Estermann, Benjamin; Lanzendörfer, Luca A.; Niedermayr, Yannick; et al. (2024)
Algorithmic reasoning is a fundamental cognitive ability that plays a pivotal role in problem-solving and decision-making processes. Reinforcement Learning (RL) has demonstrated remarkable proficiency in tasks such as motor control, handling perceptual input, and managing stochastic environments. These advancements have been enabled in part by the availability of benchmarks. In this work we introduce PUZZLES, a benchmark based on Simon Tatham's Portable Puzzle Collection, aimed at fostering progress in algorithmic and logical reasoning in RL. PUZZLES contains 40 diverse logic puzzles of adjustable sizes and varying levels of complexity; many puzzles also feature a diverse set of additional configuration parameters. The 40 puzzles provide detailed information on the strengths and generalization capabilities of RL agents. Furthermore, we evaluate various RL algorithms on PUZZLES, providing baseline comparisons and demonstrating the potential for future research. All the software, including the environment, is available at https://github.com/ETH-DISCO/rlp.
Reasoning Effort and Problem Complexity: A Scaling Analysis in LLMs
Estermann, Benjamin; Wattenhofer, Roger (2025)
Workshop on Reasoning and Planning for Large Language Models
Large Language Models (LLMs) have demonstrated remarkable text generation capabilities, and recent advances in training paradigms have led to breakthroughs in their reasoning performance. In this work, we investigate how the reasoning effort of such models scales with problem complexity. We use the infinitely scalable Tents puzzle, which has a known linear-time solution, to analyze this scaling behavior. Our results show that reasoning effort scales with problem size, but only up to a critical problem complexity. Beyond this threshold, the reasoning effort does not continue to increase, and may even decrease. This observation highlights a critical limitation in the logical coherence of current LLMs as problem complexity increases, and underscores the need for strategies to improve reasoning scalability. Furthermore, our results reveal significant performance differences between current state-of-the-art reasoning models when faced with increasingly complex logical puzzles.
The Role of Representation Learning in Advancing Deep Learning: Efficiency, Scalability, and Reasoning
Estermann, Benjamin (2025)
This thesis explores the multifaceted role of representation learning in improving the performance of deep neural networks in various applications. We delve into the paradigm of active learning, investigating its application in iterative combinatorial auctions and the integration of diversity and uncertainty-based sampling strategies in the context of self-supervised, pre-trained models. Our exploration extends to disentangled representation learning, where we introduce a novel training procedure for variational autoencoders that overcomes the challenge of hyperparameter selection and enables consistent learning of disentangled representations. We also leverage implicit neural representations for domain-agnostic super-resolution, demonstrating the ability to upscale any arbitrary data type. In addition, we address the challenge of scaling transformers to large inputs by proposing a hierarchical tree-based architecture. Finally, we investigate the reasoning capabilities of large language models. We demonstrate the feasibility of using language for reasoning in abstract visual tasks. We then introduce a benchmark for evaluating algorithmic reasoning and analyze the scaling behavior of reasoning language models on complex logic puzzles. Through these diverse investigations, this thesis contributes to a deeper understanding of representation learning and its potential to advance the development of more robust, efficient, and intelligent AI systems.

Publications 1 - 10 of 13

Benjamin Estermann

Last Name

First Name

ORCID

Organisational unit

Filters

Search Results