Related papers: Enabling Trade-offs in Machine Learning-based Matc…
Based on the success of recommender systems in e-commerce, there is growing interest in their use in matching markets (e.g., labor). While this holds potential for improving market fluidity and fairness, we show in this paper that naively…
Research on promoting cooperation among autonomous, self-regarding agents has often focused on the bi-objective optimisation problem: minimising the total incentive cost while maximising the frequency of cooperation. However, the optimal…
LLMs are increasingly used to design reward functions based on human preferences in Reinforcement Learning (RL). We focus on LLM-designed rewards for Restless Multi-Armed Bandits, a framework for allocating limited resources among agents.…
Fairness and interpretability play an important role in the adoption of decision-making algorithms across many application domains. These requirements are intended to avoid undesirable group differences and to alleviate concerns related to…
System combination is an important technique for combining the hypotheses of different machine translation systems to improve translation performance. Although early statistical approaches to system combination have been proven effective in…
Reinforcement Learning from Human Feedback (RLHF) relies on preference modeling to align machine learning systems with human values, yet the popular approach of random pair sampling with Bradley-Terry modeling is statistically limited and…
The deferred acceptance algorithm is an elegant solution to the stable matching problem that guarantees optimality and truthfulness for one side of the market. Despite these desirable guarantees, it is susceptible to strategic misreporting…
Neural machine translation is known to require large numbers of parallel training sentences, which generally prevent it from excelling on low-resource language pairs. This thesis explores the use of cross-lingual transfer learning on neural…
This paper addresses key challenges in task scheduling for multi-tenant distributed systems, including dynamic resource variation, heterogeneous tenant demands, and fairness assurance. An adaptive scheduling method based on reinforcement…
In the study of the evolution of cooperation, many mechanisms have been proposed to help overcome the self-interested cheating that is individually optimal in the Prisoners' Dilemma game. These mechanisms include assortative or networked…
Model merging has shown great promise at combining expert models, but the benefit of merging is unclear when merging "generalist" models trained on many tasks. We explore merging in the context of large (~100B) models, by recycling…
Long-term unemployment (LTU) is a challenge for both jobseekers and public employment services. Statistical profiling tools are increasingly used to predict LTU risk. Some profiling tools are opaque, black-box machine learning models, which…
The use of semi-autonomous and autonomous robotic assistants to aid in care of the elderly is expected to ease the burden on human caretakers, with small-stage testing already occurring in a variety of countries. Yet, it is likely that…
It is today acknowledged that neural network language models outperform backoff language models in applications like speech recognition or statistical machine translation. However, training these models on large amounts of data can take…
Precise and reliable climate projections are required for climate adaptation and mitigation, but Earth system models still exhibit great uncertainties. Several approaches have been developed to reduce the spread of climate projections and…
In this study, we addressed the refugee crisis through two main models. For predicting the ultimate number of refugees, we first established a Logistic Regression Model, but due to the limited data points, its prediction accuracy was…
We present ease.ml, a declarative machine learning service platform we built to support more than ten research groups outside the computer science departments at ETH Zurich for their machine learning needs. With ease.ml, a user defines the…
Schelling's model is an influential model that reveals how individual perceptions and incentives can lead to residential segregation. Inspired by a recent stream of work, we study welfare guarantees and complexity in this model with respect…
Evacuation planning is an important and challenging element in emergency management due to the high level of uncertainty and numerous players and agencies involved in the event. To address all the factors with conflicting objectives,…
When a policy prioritizes one person over another, is it because they benefit more, or because they are preferred? This paper develops a method to uncover the values consistent with observed allocation decisions. We use machine learning…