arXiv research

Paper tackles tensor decomposition for unaligned observations using RKHS and novel loss functions.

A new method, VIF, calculates influence for non-decomposable losses efficiently.

In most machine learning training paradigms a fixed, often handcrafted, loss function is assumed to be a good proxy for an underlying evaluation metric. In this work we assess this assumption by meta-learning an adaptive loss function to directly optimize the evaluation metric. We propose a sample efficient reinforceme…

Unified framework for fair regression under demographic parity.

There are a variety of Domain Adaptation (DA) scenarios subject to label sets and domain configurations, including closed-set and partial-set DA, as well as multi-source and multi-target DA. It is notable that existing DA methods are generally designed only for a specific scenario, and may underperform for scenarios th…

Large stepsize GD for logistic regression converges faster than expected.

Regularizes ML algorithms for robust multivariate analysis against distribution shifts.

A novel framework for regression with multiple experts, addressing challenges in infinite and continuous label spaces.

The fused lasso penalizes a loss function by the $L_1$ norm for both the regression coefficients and their successive differences to encourage sparsity of both. In this paper, we propose a Bayesian generalized fused lasso modeling based on a normal-exponential-gamma (NEG) prior distribution. The NEG prior is assumed in…

Neural networks solve variational inequalities for optimal stopping problems.

New algorithm reduces TV-denoising to adaptive online learning.

FourNet approximates financial transition densities using Fourier transforms.

Generative Adversarial Networks are known for their high quality outputs and versatility. However, they also suffer the mode collapse in their output data distribution. There have been many efforts to revamp GANs model and reduce mode collapse. This paper focuses on two of these models, PacGAN and VEEGAN. This paper ex…

We propose a Gradient Boosting algorithm for learning an ensemble of kernel functions adapted to the task at hand. Unlike state-of-the-art Multiple Kernel Learning techniques that make use of a pre-computed dictionary of kernel functions to select from, at each iteration we fit a kernel by approximating it as a weighte…

SA algorithms control dynamic regret in non-stationary settings with strong convexity or exp-concavity.

It is a significant challenge to design probabilistic programming systems that can accommodate a wide variety of inference strategies within a unified framework. Noting that the versatility of modern automatic differentiation frameworks is based in large part on the unifying concept of tensors, we describe a software a…

This paper deals with the unsupervised domain adaptation problem, where one wants to estimate a prediction function $f$ in a given target domain without any labeled sample by exploiting the knowledge available from a source domain where labels are known. Our work makes the following assumption: there exists a non-linea…

New algorithms for constrained online optimization with memory and predictions.

Deep quantization of neural networks (below eight bits) offers significant promise in reducing their compute and storage cost. Albeit alluring, without special techniques for training and optimization, deep quantization results in significant accuracy loss. To further mitigate this loss, we propose a novel sinusoidal r…

Neural ODEs control graph dynamics with low energy feedback.

A new privacy accountant for Gaussian differential privacy measures individual privacy losses.

Framework selects optimal historical data windows for non-stationary learning.

LibAUC optimizes X-risks for AI tasks like CID, LTR, and CLR.

The paper generalizes offset Rademacher complexities to convex and non-convex problems.

Restricted Boltzmann machines (RBMs) are a powerful class of generative models, but their training requires computing a gradient that, unlike supervised backpropagation on typical loss functions, is notoriously difficult even to approximate. Here, we show that properly combining standard gradient updates with an off-gr…

We study the problem of learning classifiers robust to universal adversarial perturbations. While prior work approaches this problem via robust optimization, adversarial training, or input transformation, we instead phrase it as a two-player zero-sum game. In this new formulation, both players simultaneously play the s…

This thesis tackles learning with multi-class abstention and multi-expert deferral, improving model reliability and efficiency.

Conventional modeling approaches have found limitations in matching the increasingly detailed neural network structures and dynamics recorded in experiments to the diverse brain functionalities. On another approach, studies have demonstrated to train spiking neural networks for simple functions using supervised learnin…

New bounds show linear predictors rarely overfit with certain optimization methods.

SOBER framework optimizes Bayesian optimization tasks efficiently.

Deep neural networks for structured prediction using kernel-induced losses.

Conditional generators learn the data distribution for each class in a multi-class scenario and generate samples for a specific class given the right input from the latent space. In this work, a method known as "Versatile Auxiliary Classifier with Generative Adversarial Network" for multi-class scenarios is presented. …

Unified approach for multimodal data prediction using synthetic data generation.

Versatile model for High Energy Physics events.

Agglomerative hierarchical clustering can be implemented with several strategies that differ in the way elements of a collection are grouped together to build a hierarchy of clusters. Here we introduce versatile linkage, a new infinite system of agglomerative hierarchical clustering strategies based on generalized mean…

New inequalities help optimize first-order algorithms for statistical risk analysis.

New method integrates topological knowledge into data embeddings.

Neural network model improves loss reserving accuracy and distribution flexibility.

New method learns output embeddings for structured prediction.

New bounds for DeepONets reduce out-of-sample error without width dependence.

This paper learns state, dynamics, and filtering algorithms together for data assimilation.

A new random forest method for multivariate distributions.

SRCA reduces high-dimensional data to lower dimensions while preserving geometric structures.

MFGs explain and enhance generative models, revealing new model types.

VeLO learns versatile optimizers from deep learning tasks.

Variational problems that involve Wasserstein distances and more generally optimal transport (OT) theory are playing an increasingly important role in data sciences. Such problems can be used to form an examplar measure out of various probability measures, as in the Wasserstein barycenter problem, or to carry out param…

Introduces Fitzpatrick losses, tighter than Fenchel-Young losses.

New multi-spiral approach improves packaging of thick membranes.