arXiv research

Paper develops a least-squares framework for learning discrete losses.

We study proper losses for discrete generative models without knowing the target distribution.

Discretizes special surfaces using Koenigs nets.

New loss function calibrates WW-hinge loss for multiclass SVM.

We consider an investor facing a classical portfolio problem of optimal investment in a log-Brownian stock and a fixed-interest bond, but constrained to choose portfolio and consumption strategies that reduce a dynamic shortfall risk measure. For continuous- and discrete-time financial markets we investigate the loss i…

Data discretization is an important step in the process of machine learning, since it is easier for classifiers to deal with discrete attributes rather than continuous attributes. Over the years, several methods of performing discretization such as Boolean Reasoning, Equal Frequency Binning, Entropy have been proposed,…

A new method trains discrete EBMs without sampling.

Direct optimization of discrete variational auto-encoders using arg max.

New method decomposes profits and losses continuously, avoiding discrete reporting issues.

The paper improves privacy accounting for discrete-valued mechanisms and the subsampled Gaussian mechanism.

The probability minimizing problem of large losses of portfolio in discrete and continuous time models is studied. This gives a generalization of quantile hedging presented in [3].

Paper proposes a method to speed up discrete diffusion models by distilling many steps into few.

Paper corrects Max-Margin loss for multi-label tasks.

Model for discrete dividend payments in continuous time models.

A new method for federated survival analysis using Cox models.

Discretizing input space improves DLN robustness against adversarial attacks.

DFM binarizes feature embeddings for fast, accurate recommendation.

Derives derivatives of risk measures for various types of portfolio losses.

StochasticRank optimizes ranking metrics efficiently and guarantees global convergence.

Paper improves PAC-Bayes bounds for various loss types.

PAGP uses physics-assisted Gaussian processes to solve and learn PDEs.

Overparameterized neural nets have a continuous set of global minima.

The reparameterization trick enables optimizing large scale stochastic computation graphs via gradient descent. The essence of the trick is to refactor each stochastic node into a differentiable function of its parameters and a random variable with fixed distribution. After refactoring, the gradients of the loss propag…

Proposes a new method for optimal graph clustering.

The goal of regression and classification methods in supervised learning is to minimize the empirical risk, that is, the expectation of some loss function quantifying the prediction error under the empirical distribution. When facing scarce training data, overfitting is typically mitigated by adding regularization term…

We develop a framework for consistent polyhedral surrogates in classification and prediction.

New algorithm improves online learning with reduced discretization.

A new CI test avoids information loss in discretized data.

This work introduces a new loss function to improve the efficiency of optimization-based PDE solvers.

Extends private optimization to non-convex problems efficiently.

Improved VAE model for discrete data through augmented training and multiscale approach.

Paper introduces scalable neural architecture for solving NP-hard problems.

Discrete Flow Maps bypass sequential prediction limits for parallel text generation.

Paper proposes DAG-DB for learning discrete DAGs via backpropagation.

We consider an arbitrage-free, discrete time and frictionless market. We prove that an investor maximising the expected utility of her terminal wealth can always find an optimal investment strategy provided that her dissatisfaction of infinite losses is infinite and her utility function is non-decreasing, continuous an…

We present a class of flexible and tractable static factor models for the term structure of joint default probabilities, the factor copula models. These high-dimensional models remain parsimonious with pair-copula constructions, and nest many standard models as special cases. The loss distribution of a portfolio of con…

This paper solves hedging in incomplete markets using neural networks.

LoRA-Curve connects independent LoRA optima through continuous low-loss valleys, improving Bayesian model averaging.

Tutorial on estimating PD using survival analysis under IFRS 9.

Study evaluates discretized arbitrage strategies in fractional financial markets.

The paper studies properties of Sliced Wasserstein energy for discrete measures.

First order discretizations of Langevin diffusion can achieve better generalization error with additional smoothness assumptions.

Work on SGDm under heavy-tailed noise, revealing its generalization properties.

Unified framework for continuous-state discrete flow matching models.

Estimating causal models from observational data is a crucial task in data analysis. For continuous-valued data, Shimizu et al. have proposed a linear acyclic non-Gaussian model to understand the data generating process, and have shown that their model is identifiable when the number of data is sufficiently large. Howe…

Graphical models for structured domains are powerful tools, but the computational complexities of combinatorial prediction spaces can force restrictions on models, or require approximate inference in order to be tractable. Instead of working in a combinatorial space, we use hinge-loss Markov random fields (HL-MRFs), an…

IDF uses integer flows for lossless compression of discrete data.

Improved vector quantization using Gaussian mixtures for better codebook utilization.