Related papers: Feedback-Enhanced Online Multiple Testing with App…

Recent studies have shown that federated learning (FL) is vulnerable to poisoning attacks that inject a backdoor into the global model. These attacks are effective even when performed by a single client, and undetectable by most existing…

The false discovery rate (FDR)---the expected fraction of spurious discoveries among all the discoveries---provides a popular statistical assessment of the reproducibility of scientific studies in various disciplines. In this work, we…

In multiple hypothesis testing, it is well known that adaptive procedures can enhance power via incorporating information about the number of true nulls present. Under independence, we establish that two adaptive false discovery rate (FDR)…

In large-scale multiple hypothesis testing problems, the false discovery exceedance (FDX) provides a desirable alternative to the widely used false discovery rate (FDR) when the false discovery proportion (FDP) is highly variable. We…

Large Language Models (LLMs) have demonstrated remarkable versatility across various domains. To further advance LLMs, we propose 'SELF' (Self-Evolution with Language Feedback), a novel approach that enables LLMs to self-improve through…

We propose an inference procedure for deep convolutional neural networks (CNNs) when partial evidence is available. Our method consists of a general feedback-based propagation approach (feedback-prop) that boosts the prediction accuracy for…

Typically, machine learning models are trained and evaluated without making any distinction between users (e.g, using traditional hold-out and cross-validation). However, this produces inaccurate performance metrics estimates in multi-user…

Interactive reinforcement learning can effectively facilitate the agent training via human feedback. However, such methods often require the human teacher to know what is the correct action that the agent should take. In other words, if the…

Recent advancements in language agents have led to significant improvements in multi-hop reasoning tasks. However, existing approaches often struggle with handling open-domain problems, which require massive information retrieval due to…

In this work, we consider an online robust Markov Decision Process (MDP) where we have the information of finitely many prototypes of the underlying transition kernel. We consider an adaptively updated ambiguity set of the prototypes and…

One core capability of large language models (LLMs) is to follow natural language instructions. However, the issue of automatically constructing high-quality training data to enhance the complex instruction-following abilities of LLMs…

Interactive feedback, where feedback flows in both directions between teacher and student, is more effective than traditional one-way feedback. However, it is often too time-consuming for widespread use in educational practice. While Large…

Reward learning typically relies on a single feedback type or combines multiple feedback types using manually weighted loss terms. Currently, it remains unclear how to jointly learn reward functions from heterogeneous feedback types such as…

Modern biomedical research frequently involves testing multiple related hypotheses, while maintaining control over a suitable error rate. In many applications the false discovery rate (FDR), which is the expected proportion of false…

Robust data-driven controllers typically rely on datasets from previous experiments, which embed information on the variability of the system parameters across past operational conditions. Complementarily, data collected online can…

Conformal selection (CS) uses calibration data to identify test inputs whose unobserved outcomes are likely to satisfy a pre-specified minimal quality requirement, while controlling the false discovery rate (FDR). Existing methods fix the…

We develop an online learning algorithm that dramatically improves the data efficiency of reinforcement learning from human feedback (RLHF). Our algorithm incrementally updates reward and language models as choice data is received. The…

We propose a new online learning model for learning with preference feedback. The model is especially suited for applications like web search and recommender systems, where preference data is readily available from implicit user feedback…

Test-time scaling via solution sampling and aggregation has become a key paradigm for improving the reasoning performance of Large Language Models (LLMs). While reward model selection is commonly employed in this approach, it often fails to…

In the online false discovery rate (FDR) problem, one observes a possibly infinite sequence of $p$-values $P_1,P_2,\dots$, each testing a different null hypothesis, and an algorithm must pick a sequence of rejection thresholds…