相关论文: Revisiting Methods for Finding Influential Example…

Human guidance is often desired in reinforcement learning to improve the performance of the learning agent. However, human insights are often mere opinions and educated guesses rather than well-formulated arguments. While opinions are…

Imitation learning is a widely used approach for training agents to replicate expert behavior in complex decision-making tasks. However, existing methods often struggle with compounding errors and limited generalization, due to the inherent…

What are the key-features that enable an information diffusion model to explain the inherent dynamic, and often competitive, nature of real-world propagation phenomena? In this paper we aim to answer this question by proposing a novel class…

Recently, influence functions present an apparatus for achieving explainability for deep neural models by quantifying the perturbation of individual train instances that might impact a test prediction. Our objectives in this paper are…

We study the problem of system identification for stochastic continuous-time dynamics, based on a single finite-length state trajectory. We present a method for estimating the possibly unstable open-loop matrix by employing properly…

Data attribution, tracing a model's prediction back to specific training data, is an important tool for interpreting sophisticated AI models. The widely used TRAK algorithm addresses this challenge by first approximating the underlying…

This dissertation investigates how reinforcement learning (RL) methods can be designed to be safe, sample-efficient, and robust. Framed through the unifying perspective of contextual-bandit RL, the work addresses two major application…

A core data-centric learning challenge is the identification of training samples that are detrimental to model performance. Influence functions serve as a prominent tool for this task and offer a robust framework for assessing training data…

Not all instances in a data set are equally beneficial for inducing a model of the data. Some instances (such as outliers or noise) can be detrimental. However, at least initially, the instances in a data set are generally considered…

Influence Functions are a standard tool for attributing predictions to training data in a principled manner and are widely used in applications such as data valuation and fairness. In this work, we present realistic incentives to manipulate…

With the rapid advancement of neural language models, the deployment of over-parameterized models has surged, increasing the need for interpretable explanations comprehensible to human inspectors. Existing post-hoc interpretability methods,…

Trust is a crucial factor affecting the adoption of machine learning (ML) models. Qualitative studies have revealed that end-users, particularly in the medical domain, need models that can express their uncertainty in decision-making…

When trying to gain better visibility into a machine learning model in order to understand and mitigate the associated risks, a potentially valuable source of evidence is: which training examples most contribute to a given behavior?…

LLMs are highly sensitive to prompt phrasing, yet standard benchmarks typically report performance using a single prompt, raising concerns about the reliability of such evaluations. In this work, we argue for a stochastic method of moments…

Network meta-analysis has been gaining prominence as an evidence synthesis method that enables the comprehensive synthesis and simultaneous comparison of multiple treatments. In many network meta-analyses, some of the constituent studies…

Imitation learning techniques have been shown to be highly effective in real-world control scenarios, such as robotics. However, these approaches not only suffer from compounding error issues but also require human experts to provide…

Learning from demonstrations has emerged as a promising paradigm for end-to-end robot control, particularly when scaled to diverse and large datasets. However, the quality of demonstration data, often collected through human teleoperation,…

Many training data attribution (TDA) methods aim to estimate how a model's behavior would change if one or more data points were removed from the training set. Methods based on implicit differentiation, such as influence functions, can be…

In this paper we describe an efficient method for providing a regression model with a sense of curiosity about its data. In the field of machine learning, our framework for representing curiosity is called Active Learning, which concerns…

Reinforcement learning has significantly enhanced the reasoning capabilities of Large Language Models (LLMs) in complex problem-solving tasks. Recently, the introduction of DeepSeek R1 has inspired a surge of interest in leveraging…