A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
New approach links machine learning reliability to epistemic uncertainty.
This work explores a social learning problem with agents having nonidentical noise variances and mismatched beliefs. We consider an -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…
New decision-theoretic characterization separates belief and decision posteriors.
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…
Improved error correction using neural networks and belief propagation.
A significant theoretical advantage of search-and-score methods for learning Bayesian Networks is that they can accept informative prior beliefs for each possible network, thus complementing the data. In this paper, a method is presented for assigning priors based on beliefs on the presence or absence of certain paths …
In this paper we introduce deep Gaussian process (GP) models. Deep GPs are a deep belief network based on Gaussian process mappings. The data is modeled as the output of a multivariate GP. The inputs to that Gaussian process are then governed by another GP. A single layer model is equivalent to a standard GP or the GP …
In the present paper a model of a market consisting of real and financial interacting sectors is studied. Agents populating the stock market are assumed to be not able to observe the true underlying fundamental, and their beliefs are biased by either optimism or pessimism. Depending on the relevance they give to belief…
This work investigates the case of a network of agents that attempt to learn some unknown state of the world amongst the finitely many possibilities. At each time step, agents all receive random, independently distributed private signals whose distributions are dependent on the unknown state of the world. However, it m…
Paper shows statistical learning can't always lead to true knowledge.
We consider the problem of estimating the expected value of information (the knowledge gradient) for Bayesian learning problems where the belief model is nonlinear in the parameters. Our goal is to maximize some metric, while simultaneously learning the unknown parameters of the nonlinear belief model, by guiding a seq…
Diversification increases systemic risk, contrary to belief.
In this paper we provide a pricing-hedging duality for the model-independent superhedging price with respect to a prediction set , where the superhedging property needs to hold pathwise, but only for paths lying in . For any Borel measurable claim which is bounded from below, the superhedging …
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…
Learning latent variable models with stochastic variational inference is challenging when the approximate posterior is far from the true posterior, due to high variance in the gradient estimates. We propose a novel rejection sampling step that discards samples from the variational posterior which are assigned low likel…
Imbalanced data with a skewed class distribution are common in many real-world applications. Deep Belief Network (DBN) is a machine learning technique that is effective in classification tasks. However, conventional DBN does not work well for imbalanced data classification because it assumes equal costs for each class.…
For many large undirected models that arise in real-world applications, exact maximumlikelihood training is intractable, because it requires computing marginal distributions of the model. Conditional training is even more difficult, because the partition function depends not only on the parameters, but also on the obse…
Learning rate decay (lrDecay) is a \emph{de facto} technique for training modern neural networks. It starts with a large learning rate and then decays it multiple times. It is empirically observed to help both optimization and generalization. Common beliefs in how lrDecay works come from the optimization analysis of (S…
Crowdsourcing systems are popular for solving large-scale labelling tasks with low-paid workers. We study the problem of recovering the true labels from the possibly erroneous crowdsourced labels under the popular Dawid-Skene model. To address this inference problem, several algorithms have recently been proposed, but …
Study finds gender bias in human evaluators and shows how machine learning can mitigate it.
Financial economic models often assume that investors know (or agree on) the fundamental value of the shares of the firm, easing the passage from the individual to the collective dimension of the financial system generated by the Share Exchange over time. Our model relaxes that heroic assumption of one unique "true val…
Helps visually impaired users make better decisions by adjusting their observations.
Bayesian methods improve group testing for identifying infected patients.
Study market efficiency under partial information using SDEs and optimization.
The paper proposes a method to calibrate evidential clustering using bootstrapped finite mixture models.
Study on robust utility maximization with nonconcave utility functions under projective determinacy.
No-regret learning with strategic experts, incentivized.
Generalized belief propagation converges to optimal solutions on graphs with motifs.
Study risk sharing with Lambda VaR under diverse beliefs.
LLMs' explanations are often insufficient and vary with input distribution.
This paper optimizes liquidity provision in automated market makers using auction theory.
Determining how to appropriately select the tuning parameter is essential in penalized likelihood methods for high-dimensional data analysis. We examine this problem in the setting of penalized likelihood methods for generalized linear models, where the dimensionality of covariates p is allowed to increase exponentiall…
Unified framework explains retirement and annuitization decisions under age-dependent mortality.
Belief propagation recovers backpropagation results.
Method identifies causal drivers from background features.
Bayesian models can be tricked into believing false data.
New framework analyzes belief evolution in social networks.
Agent decides when to measure latent states in RL to improve efficiency.
Study optimal liquidation with incomplete trend information and multiplicative price impact.
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, …
Bounds on factual and counterfactual distributions under measurement error in discrete models.
This paper means to correct an error by the authors for the composite case in the paper "Lens Spaces, Isospectral on Forms but not on Functions", published in LMS J. Comput. Math.} 9 (2006), 270-286. All calculations and examples presented in \cite{GM} for prime remain valid, and we include detailed calculation…
While statistics focusses on hypothesis testing and on estimating (properties of) the true sampling distribution, in machine learning the performance of learning algorithms on future data is the primary issue. In this paper we bridge the gap with a general principle (PHI) that identifies hypotheses with best predictive…
Cold posteriors improve Bayesian neural networks by reducing overestimation of aleatoric uncertainty.
XGBoost is often presented as the algorithm that wins every ML competition. Surprisingly, this is true even though predictions are piecewise constant. This might be justified in high dimensional input spaces, but when the number of features is low, a piecewise linear model is likely to perform better. XGBoost was exten…
New method removes interference bias in causal models.
We focus on credal nets, which are graphical models that generalise Bayesian nets to imprecise probability. We replace the notion of strong independence commonly used in credal nets with the weaker notion of epistemic irrelevance, which is arguably more suited for a behavioural theory of probability. Focusing on direct…
We study the problem of cooperative inference where a group of agents interact over a network and seek to estimate a joint parameter that best explains a set of observations. Agents do not know the network topology or the observations of other agents. We explore a variational interpretation of the Bayesian posterior de…