arXiv research

A new mechanism reduces expert belief regret in online forecasting.

New approach limits regret in non-stationary bandits.

New algorithm reduces regret in strategic prediction problem.

No-regret learning with strategic experts, incentivized.

The study proves necessary conditions for robust decision-making in uncertain environments.

New theorems show agents need specific internal structures to perform well under uncertainty.

Study on deep neural networks for reward modeling with pairwise comparison data.

Improved POMDP regret to sqrt(T) with known observation model.

Bayesian methods suffer from the problem of how to specify prior beliefs. One interesting idea is to consider worst-case priors. This requires solving a stochastic zero-sum game. In this paper, we extend well-known results from bandit theory in order to discover minimax-Bayes policies and discuss when they are practica…

πBO augments BO with user beliefs for better hyperparameter optimization.

Bayesian optimization guided by experimenter intuition and beliefs.

Recursive experts improve dynamic sequential learning systems.

New algorithm learns POMDPs with known observation model efficiently.

In evaluating prediction markets (and other crowd-prediction mechanisms), investigators have repeatedly observed a so-called "wisdom of crowds" effect, which roughly says that the average of participants performs much better than the average participant. The market price---an average or at least aggregate of traders' b…

New Thompson Sampling for partially observed context bandits reduces regret logarithmically with time.

Research in reinforcement learning has produced algorithms for optimal decision making under uncertainty that fall within two main types. The first employs a Bayesian framework, where optimality improves with increased computational time. This is because the resulting planning task takes the form of a dynamic programmi…

Novel Bayesian approach for non-stationary linear contextual bandits.

Generalized belief propagation converges to optimal solutions on graphs with motifs.

Study risk sharing with Lambda VaR under diverse beliefs.

Belief propagation recovers backpropagation results.

New framework analyzes belief evolution in social networks.

Proposes a new sampling method for online learning with cumulative oversampling.

We consider the problem of imitation learning from expert demonstrations in partially observable Markov decision processes (POMDPs). Belief representations, which characterize the distribution over the latent states in a POMDP, have been modeled using recurrent neural networks and probabilistic latent variable models, …

New method reduces GP bandit complexity while maintaining good performance.

Improved error correction using neural networks and belief propagation.

Bayesian approach improves online prediction accuracy without distributional assumptions.

NBF combines deep learning with classical filtering for better belief tracking.

This thesis investigates belief propagation's performance in graphical models with loops.

FORBES learns flexible belief states for POMDPs using normalizing flows.

This work explores a social learning problem with agents having nonidentical noise variances and mismatched beliefs. We consider an $N$-agent binary hypothesis test in which each agent sequentially makes a decision based not only on a private observation, but also on preceding agents' decisions. In addition, the agents…

Belief Propagation algorithms are instruments used broadly to solve graphical model optimization and statistical inference problems. In the general case of a loopy Graphical Model, Belief Propagation is a heuristic which is quite successful in practice, even though its empirical success, typically, lacks theoretical gu…

Model captures decision-making under bounded rationality with prior beliefs and market feedback.

By elaborating on the notion of linear belief functions (Dempster 1990; Liu 1996), we propose an elementary approach to knowledge representation for expert systems using linear belief functions. We show how to use basic matrices to represent market information and financial knowledge, including complete ignorance, stat…

This paper optimizes reinsurance contracts with belief differences between insurer and reinsurer.

Deep belief networks are a powerful way to model complex probability distributions. However, learning the structure of a belief network, particularly one with hidden units, is difficult. The Indian buffet process has been used as a nonparametric Bayesian prior on the directed structure of a belief network with a single…

In this paper I empirically investigate prediction markets for binary options. Advocates of prediction markets have suggested that asset prices are consistent estimators of the "true" probability of a state of the world being realized. I test whether the market reaches a "consensus." I find little evidence for converge…

New algorithm reduces communication in distributed learning by sharing compressed beliefs.

New $\alpha$-BP algorithm improves belief propagation for graphs with loops.

New group testing method uses Belief Propagation for accurate screening.

Belief propagation (BP) can do exact inference in loop-free graphs, but its performance could be poor in graphs with loops, and the understanding of its solution is limited. This work gives an interpretable belief propagation rule that is actually minimization of a localized $α$-divergence. We term this algorithm as $α…

The paper explains stock market predictability through a model of heterogeneous beliefs.

A number of problems in statistical physics and computer science can be expressed as the computation of marginal probabilities over a Markov random field. Belief propagation, an iterative message-passing algorithm, computes exactly such marginals when the underlying graph is a tree. But it has gained its popularity as …

Study shows price bubbles can exist even with heterogeneous beliefs.

A method for eliciting expert beliefs using preferential questions and normalizing flows.

Develops a framework for quantifying agentic AI model risk using LLM-inferred Bayesian state filters.

Algorithm finds a simplified model for reinforcement learning under agent limitations.

This paper presents a general framework for studying diverse beliefs in dynamic economies. Within this general framework, the characterization of a central-planner general equilbrium turns out to be very easy to derive, and leads to a range of interesting applications. We show how for an economy with log investors hold…

Recurrent networks learn beliefs from history in partially observable environments.