arXiv research

Investigates a Kyle model with imperfect information and risk aversion.

New method robustly discovers causal relationships from imperfect data.

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…

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…

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

Algorithm learns NE in imperfect information games with imperfect feedback.

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

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…

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…

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

Bayesian framework mixes imperfect models for improved predictions.

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

Improves off-policy evaluation with imperfect annotations.

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…

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…

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

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

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

Policy gradient method proves convergence in imperfect-information games.

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

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

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

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

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

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

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

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.

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

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…

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

New probabilistic approaches offer recourse recommendations even when causal models are imperfect.

Develops methods to improve demand counterfactuals from imperfect proxies.

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…

RLCFR improves CFR's generalization in imperfect information games.

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

We derive asset pricing formula for markets with incomplete information and subjective views.

End-to-end framework learns from imperfect annotations directly.

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…

We study pricing and (super)hedging for American options in an imperfect market model with default, where the imperfections are taken into account via the nonlinearity of the wealth dynamics. The payoff is given by an RCLL adapted process $(ξ_t)$. We define the {\em seller's superhedging price} of the American option a…

This thesis tackles data imperfections in ML, proposing methods to prevent discrimination and spurious feature learning.

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…

Estimates treatment effects in randomized experiments with non-compliance.

Study completes financial markets in complex models without external probabilities.

Integrating model-free and model-based approaches in reinforcement learning has the potential to achieve the high performance of model-free algorithms with low sample complexity. However, this is difficult because an imperfect dynamics model can degrade the performance of the learning algorithm, and in sufficiently com…

The paper analyzes insurance pricing and capital allocation in imperfect markets.