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.
Improved sample complexity for diffusion models without needing empirical risk minimizers.
R package for Bayesian empirical likelihood sampling using HMC.
Paper analyzes high-dimensional portfolio risks and finds empirical out-of-sample relative loss is more reliable.
Neural network accuracy improves with denser training samples.
Corrects sample selection bias in empirical risk minimization using importance sampling.
This study examines biases in flow matching samplers using finite-sample estimation.
We give improved constants for data dependent and variance sensitive confidence bounds, called empirical Bernstein bounds, and extend these inequalities to hold uniformly over classes of functionswhose growth function is polynomial in the sample size n. The bounds lead us to consider sample variance penalization, a nov…
Importance sampling has become an important tool for the computation of tail-based risk measures. Since such quantities are often determined mainly by rare events standard Monte Carlo can be inefficient and importance sampling provides a way to speed up computations. This paper considers moderate deviations for the wei…
Detect changes in noisy dynamical systems using empirical approximations and finite-sample bounds.
Backward exploration reduces sample complexity in policy evaluation.
We explain theoretically a curious empirical phenomenon: "Approximating a matrix by deterministically selecting a subset of its columns with the corresponding largest leverage scores results in a good low-rank matrix surrogate". To obtain provable guarantees, previous work requires randomized sampling of the columns wi…
We consider distributed convex optimization problems originated from sample average approximation of stochastic optimization, or empirical risk minimization in machine learning. We assume that each machine in the distributed computing system has access to a local empirical loss function, constructed with i.i.d. data sa…
A neural network method estimates densities from characteristic functions.
A new sampling method using log-concave Markov chains.
We describe a method to determine the eigenvalue density of empirical covariance matrix in the presence of correlations between samples. This is a straightforward generalization of the method developed earlier by the authors for uncorrelated samples. The method allows for exact determination of the experimental spectru…
Recently theoretical guarantees have been obtained for matrix completion in the non-uniform sampling regime. In particular, if the sampling distribution aligns with the underlying matrix's leverage scores, then with high probability nuclear norm minimization will exactly recover the low rank matrix. In this article, we…
Changes (returns) in stock index prices and exchange rates for currencies are argued, based on empirical data, to obey a stable distribution with characteristic exponent for short sampling intervals and a Gaussian distribution for long sampling intervals. In order to explain this phenomenon, an Ehrenfest model…
We develop an approach to risk minimization and stochastic optimization that provides a convex surrogate for variance, allowing near-optimal and computationally efficient trading between approximation and estimation error. Our approach builds off of techniques for distributionally robust optimization and Owen's empiric…
Improved multi-group learning with group-realizable concepts.
Exact distribution of split conformal prediction coverage found.
In this work, we empirically explore the question: how can we assess the quality of samples from some target distribution? We assume that the samples are provided by some valid Monte Carlo procedure, so we are guaranteed that the collection of samples will asymptotically approximate the true distribution. Most current …
Develops robust MDPs for unknown disturbances with performance guarantees.
Random features provide a practical framework for large-scale kernel approximation and supervised learning. It has been shown that data-dependent sampling of random features using leverage scores can significantly reduce the number of features required to achieve optimal learning bounds. Leverage scores introduce an op…
Proves minimax sample complexity for turn-based stochastic games.
The paper provides theoretical guarantees for optimized sampling in compressed sensing, showing error vanishes with more measurements.
Solves memorization in diffusion models for manifold data.
Paper improves Thompson Sampling for linear contextual bandits.
Thompson sampling, a Bayesian method for balancing exploration and exploitation in bandit problems, has theoretical guarantees and exhibits strong empirical performance in many domains. Traditional Thompson sampling, however, assumes perfect compliance, where an agent's chosen action is treated as the implemented actio…
The best-known and most commonly used distribution-property estimation technique uses a plug-in estimator, with empirical frequency replacing the underlying distribution. We present novel linear-time-computable estimators that significantly "amplify" the effective amount of data available. For a large variety of distri…
A new autoencoder method uses empirical beta copulas for generating data.
Empirical risk minimization is the main tool for prediction problems, but its extension to relational data remains unsolved. We solve this problem using recent ideas from graph sampling theory to (i) define an empirical risk for relational data and (ii) obtain stochastic gradients for this empirical risk that are autom…
New algorithm reduces sample complexity for Top Two method.
A new two-step MH method for Bayesian EL computation.
The paper optimizes RV estimation by efficient sampling in time-changed diffusion models.
A new method for generating samples without training, using smoothed score matching.
The paper proves concentration inequalities for two-sample rank processes and applies them to ranking performance criteria.
Proposes methods to learn from biased samples, ensuring robust decision rules.
Kurtosis is seen as a measure of the discrepancy between the observed data and a Gaussian distribution and is defined when the 4th moment is finite. In this work an empirical study is conducted to investigate the behaviour of the sample estimate of kurtosis with respect to sample size and the tail index when applied to…
Efficient Reinforcement Learning usually takes advantage of demonstration or good exploration strategy. By applying posterior sampling in model-free RL under the hypothesis of GP, we propose Gaussian Process Posterior Sampling Reinforcement Learning(GPPSTD) algorithm in continuous state space, giving theoretical justif…
We provide rigorous guarantees on learning with the weighted trace-norm under arbitrary sampling distributions. We show that the standard weighted trace-norm might fail when the sampling distribution is not a product distribution (i.e. when row and column indexes are not selected independently), present a corrected var…
New statistical test for change-point detection using relative entropy.
Optimizes bilevel empirical risk minimization with improved oracle calls.
New method estimates Schrödinger bridge potentials via empirical risk minimization.
The paper provides bounds for the empirical angular measure and applies them to improve statistical learning in extreme regions.
We propose a novel approach for sampling realistic financial correlation matrices. This approach is based on generative adversarial networks. Experiments demonstrate that generative adversarial networks are able to recover most of the known stylized facts about empirical correlation matrices estimated on asset returns.…
We discuss how maximum entropy methods may be applied to the reconstruction of Markov processes underlying empirical time series and compare this approach to usual frequency sampling. It is shown that, at least in low dimension, there exists a subset of the space of stochastic matrices for which the MaxEnt method is mo…
This work analyzes IRM and ERM from sample complexity perspective, revealing different behaviors under various distribution shifts.
Proposes a method to train classifiers with delayed feedback using a time window.