arXiv research

A new formula reveals symmetries between mean excess and ES functions.

We use a continuous-time random walk (CTRW) to model market fluctuation data from times when traders experience excessive losses or excessive profits. We analytically derive "superstatistics" that accurately model empirical market activity data (supplied by Bogachev, Ludescher, Tsallis, and Bunde)that exhibit transitio…

Study excess capacity in neural networks using Rademacher complexity.

The paper bounds the excess risk of deep neural networks for weakly dependent processes.

Study excess risk in statistical inference with transformations.

Optimizes gradual reduction of excess carbon emissions to net-zero.

Mathematical study of excess growth rate connects info theory with finance.

New method estimates model risk without knowing function class.

In statistical learning theory, convex surrogates of the 0-1 loss are highly preferred because of the computational and theoretical virtues that convexity brings in. This is of more importance if we consider smooth surrogates as witnessed by the fact that the smoothness is further beneficial both computationally- by at…

We prove that a metric measure space $(X,d,m)$ satisfying finite dimensional lower Ricci curvature bounds and whose Sobolev space $W^{1,2}$ is Hilbert is rectifiable. That is, a $RCD^*(K,N)$-space is rectifiable, and in particular for $m$-a.e. point the tangent cone is unique and euclidean of dimension at most $N$. The…

The overarching goal of this paper is to derive excess risk bounds for learning from exp-concave loss functions in passive and sequential learning settings. Exp-concave loss functions encompass several fundamental problems in machine learning such as squared loss in linear regression, logistic loss in classification, a…

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…

New method refines model-free evaluation of complex machine learning models.

Private algorithms minimize population loss with optimal rate.

We consider a standard binary classification problem. The performance of any binary classifier based on the training data is characterized by the excess risk. We study Bahadur's type exponential bounds on the minimax accuracy confidence function based on the excess risk. We study how this quantity depends on the comple…

Study non-asymptotic bounds for robust estimators under misspecified models.

Optimal private ERM and SCO with subquadratic gradient complexity.

New DP algorithm improves privacy and efficiency for convex optimization.

New method for unbiased regression reduces excess risk.

This paper analyzes neural network classifiers' performance in binary classification.

This paper concerns integral varifolds of arbitrary dimension in an open subset of Euclidean space with its first variation given by either a Radon measure or a function in some Lebesgue space. Pointwise decay results for the quadratic tilt-excess are established for those varifolds. The results are optimal in terms of…

Improved DP SO with large Lipschitz parameters, handling outliers and heavy-tailed data.

We prove a new and general concentration inequality for the excess risk in least-squares regression with random design and heteroscedastic noise. No specific structure is required on the model, except the existence of a suitable function that controls the local suprema of the empirical process. So far, only the case of…

This paper analyzes multi-pass SGD for least squares, improving generalization bounds.

The paper calculates how fast optimal investment strategies approach CRRA strategies in stochastic factor models.

Bayesian model for discrete data with conditional transformations.

Second-order methods improve differential privacy in convex optimization.

Paper bounds excess risk in robust empirical risk minimization for heavy-tailed distributions.

The paper analyzes classification algorithms on Korobov space and derives learning rates.

New algorithm achieves optimal privacy and efficiency in non-Euclidean convex optimization.

We present new excess risk bounds for general unbounded loss functions including log loss and squared loss, where the distribution of the losses may be heavy-tailed. The bounds hold for general estimators, but they are optimized when applied to $η$-generalized Bayesian, MDL, and empirical risk minimization estimators. …

Paper introduces robust kernel ridge regression using Cauchy loss for handling various noise types.

This research improves PAC-Bayesian bounds for classification tasks using convexified loss.

AlphaZeroBeta uses deep reinforcement learning for market-neutral portfolios, outperforming traditional methods.

Investor-driven information diffusion affects excess comovement in China and the U.S. markets.

Study uses spectral risk for learning with heavy-tailed data.

The paper analyzes the generalization of deep neural networks for metric and similarity learning.

Paper tackles robust deep learning from weakly dependent data with unbounded loss and input.

The paper optimizes insurance strategies for two collaborating business lines.

Paper provides a rigorous proof of the index theorem for economists.

New method simplifies analysis of exercise timing for ambiguous integral option contracts.

Improves statistical learning bounds with self-concordant losses.

The paper provides risk bounds for learning many response functions using linear regression.

Deep neural networks classify unbounded Gaussian mixture data without dimensionality issues.

New distribution resolves excess volatility puzzle in finance.

Paper develops an online learning algorithm for functional data models.

Study optimizes prediction intervals in conformal regression.

New tool detects 'fleeting modes' causing excess risk in financial markets.