Education
Conformal Meta-learners for Predictive Inference of Individual Treatment Effects
Previous work has focused primarily on developing ML-based "meta-learners" that can provide point estimates of the conditional
Train Once, Get a Family: State-Adaptive Balances for Offline-to-Online Reinforcement Learning
Easily integrated, FamO2O statistically enhances existing algorithms' performance.
Structured Prediction with Stronger Consistency Guarantees
In most applications, the output labels of learning problems have some structure that is crucial to consider. This includes natural language processing applications, where the output may be a sentence, a sequence of parts-of-speech tags, a parse tree, or a dependency graph.
Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena
We argue that this discrepancy primarily arises due to existing evaluation that only measures LLMs'
ELF-R
This mostly includes tasks with multifaceted objectives, such as dialogue response generation, or tasks with hard-to-define goals, such as enhancing program readability.
Estimating Causal Effects Identifiable from a Combination of Observations and Experiments Y onghan Jung 1, Ivรกn Dรญaz
Learning cause and effect relations is arguably one of the central challenges found throughout the data sciences. Formally, determining whether a collection of observational and interventional distributions can be combined to learn a target causal relation is known as the problem of generalized identification (or g-identification) [ Lee et al., 2019 ]. Although g-identification has been well understood and solved in theory, it turns out to be challenging to apply these results in practice, in particular when considering the estimation of the target distribution from finite samples. In this paper, we develop a new, general estimator that exhibits multiply robustness properties for g-identifiable causal functionals. Specifically, we show that any g-identifiable causal effect can be expressed as a function of generalized multi-outcome sequential back-door adjustments that are amenable to estimation. We then construct a corresponding estimator for the g-identification expression that exhibits robustness properties to bias. We analyze the asymptotic convergence properties of the estimator. Finally, we illustrate the use of the proposed estimator in experimental studies. Simulation results corroborate the theory.
On the Minimax Regret for Online Learning with Feedback Graphs
In this work, we improve on the upper and lower bounds for the regret of online learning with strongly observable undirected feedback graphs.