arXiv research

The study examines how verifier imperfections impact test-time scaling techniques.

FUSE improves verification quality without ground truth labels.

DNCF framework recovers real scenes from imperfect images robustly.

Verification helps prevent model collapse when training on synthesized data.

The paper tackles learning from imperfect human feedback, especially in dueling bandit problems.

Investigates a Kyle model with imperfect information and risk aversion.

Imitation learning (IL) aims to learn an optimal policy from demonstrations. However, such demonstrations are often imperfect since collecting optimal ones is costly. To effectively learn from imperfect demonstrations, we propose a novel approach that utilizes confidence scores, which describe the quality of demonstrat…

We study the effect of imperfect training data labels on the performance of classification methods. In a general setting, where the probability that an observation in the training dataset is mislabelled may depend on both the feature vector and the true label, we bound the excess risk of an arbitrary classifier trained…

In this paper we investigate the Follow the Regularized Leader dynamics in sequential imperfect information games (IIG). We generalize existing results of Poincaré recurrence from normal-form games to zero-sum two-player imperfect information games and other sequential game settings. We then investigate how adapting th…

Policy gradient method proves convergence in imperfect-information games.

New method robustly discovers causal relationships from imperfect data.

Formalizes weak and strong verification for LLMs, controlling errors without assumptions.

Simulator imperfection, often known as model error, is ubiquitous in practical data assimilation problems. Despite the enormous efforts dedicated to addressing this problem, properly handling simulator imperfection in data assimilation remains to be a challenging task. In this work, we propose an approach to dealing wi…

Study on teaching with imperfect knowledge, showing its impact on optimal teaching sets.

There has been an increased interest in multimodal language processing including multimodal dialog, question answering, sentiment analysis, and speech recognition. However, naturally occurring multimodal data is often imperfect as a result of imperfect modalities, missing entries or noise corruption. To address these c…

The study categorizes reward errors in reinforcement learning, finding some can be beneficial.

JPS improves joint policies for multi-agent collaboration in imperfect information games.

We discuss a general notion of "sparsity structure" and associated recoveries of a sparse signal from its linear image of reduced dimension possibly corrupted with noise. Our approach allows for unified treatment of (a) the "usual sparsity" and "usual $\ell_1$ recovery," (b) block-sparsity with possibly overlapping blo…

Algorithm learns NE in imperfect information games with imperfect feedback.

Model financial markets using open quantum systems to understand market imperfections.

Improves off-policy evaluation with imperfect annotations.

Study learns optimal strategies in imperfect information games with self-play.

Researchers develop methods for causal inference with imperfect instrumental variables.

Paper solves learning imperfect-information games with fewer episodes.

We study pricing and superhedging strategies for game options in an imperfect market with default. We extend the results obtained by Kifer in \cite{Kifer} in the case of a perfect market model to the case of an imperfect market with default, when the imperfections are taken into account via the nonlinearity of the weal…

Recently, network lasso has drawn many attentions due to its remarkable performance on simultaneous clustering and optimization. However, it usually suffers from the imperfect data (noise, missing values etc), and yields sub-optimal solutions. The reason is that it finds the similar instances according to their feature…

Bayesian framework mixes imperfect models for improved predictions.

Selective planning with imperfect models reduces harmful effects of model inadequacy.

Model financial network dynamics to avoid systemic risk.

New method uses imperfect LLM annotations for valid statistical inference in social science.

DREAM learns optimal strategies in imperfect games without needing a simulator.

Study on liquidity and market efficiency in auction games with imperfect information.

This paper explores how imperfect reward models can improve online RLHF.

ReD improves LLM inference efficiency at fixed budget, reducing attempts and cost.

New algorithm uses imperfect advice to improve online bipartite matching performance.

A new framework improves VaR recalibration by balancing reliance on imperfect volatility proxies.

Combining LETKF and RC improves chaotic system prediction from noisy, sparse data.

In this paper, we study Reinforcement Learning from Demonstrations (RLfD) that improves the exploration efficiency of Reinforcement Learning (RL) by providing expert demonstrations. Most of existing RLfD methods require demonstrations to be perfect and sufficient, which yet is unrealistic to meet in practice. To work o…

We present a novel methodology for predicting future outcomes that uses small numbers of individuals participating in an imperfect information market. By determining their risk attitudes and performing a nonlinear aggregation of their predictions, we are able to assess the probability of the future outcome of an uncert…

Paper introduces a method to learn physics between digital twins using imperfect models.

Bayesian framework calibrates imperfect models using physics-informed priors and Hamiltonian Monte Carlo.

Estimates treatment effects in randomized experiments with non-compliance.

Training a source model optimally for its own task is suboptimal for downstream transfer.

RLCFR improves CFR's generalization in imperfect information games.

In a model with no given probability measure, we consider asset pricing in the presence of frictions and other imperfections and characterize the property of coherent pricing, a notion related to (but much weaker than) the no arbitrage property. We show that prices are coherent if and only if the set of pricing measure…

The paper analyzes knowledge distillation in wide neural networks, providing theoretical insights and practical implications.

Study cooperative bandit learning with imperfect communication, achieving near-optimal performance.

The paper proposes a new framework to generate synthetic data with human-like imperfections to prevent model collapse.