Related papers: Data-Driven Preference Sampling for Pareto Front L…

Deep neural networks have excelled on a wide range of problems, from vision to language and game playing. Neural networks very gradually incorporate information into weights as they process data, requiring very low learning rates. If the…

In the application of machine learning to real-life decision-making systems, e.g., credit scoring and criminal justice, the prediction outcomes might discriminate against people with sensitive attributes, leading to unfairness. The commonly…

This paper investigates image inpainting with preference alignment. Instead of introducing a novel method, we go back to basics and revisit fundamental problems in achieving such alignment. We leverage the prominent direct preference…

Randomized methods of neural network learning suffer from a problem with the generation of random parameters as they are difficult to set optimally to obtain a good projection space. The standard method draws the parameters from a fixed…

Decision-making problems often feature uncertainty stemming from heterogeneous and context-dependent human preferences. To address this, we propose a sequential learning-and-optimization pipeline to learn preference distributions and…

Preference-based learning of reward functions, where the reward function is learned using comparison data, has been well studied for complex robotic tasks such as autonomous driving. Existing algorithms have focused on learning reward…

Recent advances in language modeling have underscored the role of preference feedback in enhancing model performance. This paper investigates the conditions under which preference feedback improves parameter estimation in classes of…

Fairness in federated learning has emerged as a critical concern, aiming to develop an unbiased model among groups (e.g., male or female) of diverse sensitive features. However, there is a trade-off between model performance and fairness,…

Offline multi-objective optimization aims to identify Pareto-optimal solutions given a dataset of designs and their objective values. In this work, we propose a preference-guided diffusion model that generates Pareto-optimal designs by…

Instruction data selection aims to identify a high-quality subset from the training set that matches or exceeds the performance of the full dataset on target tasks. Existing methods focus on the instruction-to-response mapping, but neglect…

Ensuring that large language models (LLMs) are both helpful and harmless is a critical challenge, as overly strict constraints can lead to excessive refusals, while permissive models risk generating harmful content. Existing approaches,…

Diffusion models have achieved remarkable success in conditional image generation, yet their outputs often remain misaligned with human preferences. To address this, recent work has applied Direct Preference Optimization (DPO) to diffusion…

Transfer learning is a popular practice in deep neural networks, but fine-tuning of large number of parameters is a hard task due to the complex wiring of neurons between splitting layers and imbalance distributions of data in pretrained…

Large language models (LLMs) generally utilize a consistent data distribution throughout the pretraining process. However, as the model's capability improves, it is intuitive that its data preferences dynamically change, indicating the need…

Recommender systems can automatically recommend users with items that they probably like. The goal of them is to model the user-item interaction by effectively representing the users and items. Existing methods have primarily learned the…

Determinantal Point Processes (DPPs) provide an elegant and versatile way to sample sets of items that balance the point-wise quality with the set-wise diversity of selected items. For this reason, they have gained prominence in many…

Preference-based reinforcement learning (RL) is a key paradigm for aligning policies with human judgments, yet its theoretical behavior in distributed settings where preference data are fragmented across heterogeneous users remains poorly…

Research on time series forecasting has predominantly focused on developing methods that improve accuracy. However, other criteria such as training time or latency are critical in many real-world applications. We therefore address the…

Multi-objective reinforcement learning (MORL) approaches have emerged to tackle many real-world problems with multiple conflicting objectives by maximizing a joint objective function weighted by a preference vector. These approaches find…

We propose a novel numerical approach to compute the Pareto front in multivariate polynomial multi-objective optimization problems. When the objective functions and (equality) constraints are multivariate polynomials, the Pareto front,…