arXiv research

New method combines spectral and sparse methods for Gaussian processes.

Semi-parametric framework for nonlinear system identification

Gaussian processes (GPs) provide a powerful non-parametric framework for reasoning over functions. Despite appealing theory, its superlinear computational and memory complexities have presented a long-standing challenge. State-of-the-art sparse variational inference methods trade modeling accuracy against complexity. H…

PerPCA separates unique and shared features from heterogeneous data.

Muon optimizer simplifies matrix optimization with spectral orthogonalization.

MuonEq improves training of matrix-valued parameters by rebalancing momentum before orthogonalization.

New equations simplify gauge-theoretic Khovanov homology solutions.

Unified q-learning for mean-field jump-diffusion models with unobservable population distribution.

Enhances Gaussian processes with spherical features for better scalability and flexibility.

Introduces tunable basis functions for Gaussian processes.

In this paper, we introduce McTorch, a manifold optimization library for deep learning that extends PyTorch. It aims to lower the barrier for users wishing to use manifold constraints in deep learning applications, i.e., when the parameters are constrained to lie on a manifold. Such constraints include the popular orth…

Inner product-based convolution has been a central component of convolutional neural networks (CNNs) and the key to learning visual representations. Inspired by the observation that CNN-learned features are naturally decoupled with the norm of features corresponding to the intra-class variation and the angle correspond…

PeL separates sensory interface optimization from decision learning.

We investigate finite-time decoupled convergence in nonlinear two-time-scale stochastic approximation.

In this paper, we present a new nonintrusive reduced basis method when a cheap low-fidelity model and expensive high-fidelity model are available. The method relies on proper orthogonal decomposition (POD) to generate the high-fidelity reduced basis and a shallow multilayer perceptron to learn the high-fidelity reduced…

Defines and parametrizes $\mathfrak{sl}(2)$-type singular fibres in symplectic and odd orthogonal Hitchin systems.

Spectral decoupling improves neural network generalization in medical imaging.

Decoupled GCN is shown to be equivalent to label propagation.

We develop a mean-field theory for multi-component ICA in high dimensions.

We investigate probabilistic decoupling of labels supplied for training, from the underlying classes for prediction. Decoupling enables an inference scheme general enough to implement many classification problems, including supervised, semi-supervised, positive-unlabelled, noisy-label and suggests a general solution to…

The paper proposes a decoupled approach to efficiently estimate CoVaR, a measure of systemic financial risk.

This paper investigates the effectiveness of decoupled weight decay at the start of training.

Clarifies method of phase synchronization for decoupling linear differential equations.

Kahler geometry explains decoupling of Kerr perturbations.

AdaDEM decouples EM into two parts to improve class overlap and uncertainty.

Recent variants improve knowledge distillation performance.

New algorithms for interpreting complex multivariate functions.

We establish decoupled functional CLTs for two-time-scale stochastic approximation.

Current reinforcement learning (RL) methods can successfully learn single tasks but often generalize poorly to modest perturbations in task domain or training procedure. In this work, we present a decoupled learning strategy for RL that creates a shared representation space where knowledge can be robustly transferred. …

Stylized facts can be regarded as constraints for any modeling attempt of price dynamics on a financial market, in that an empirically reasonable model has to reproduce these stylized facts at least qualitatively. The dynamics of market prices is modeled on a macro-level as the result of the dynamic coupling of two dyn…

Backpropagation algorithm is indispensable for the training of feedforward neural networks. It requires propagating error gradients sequentially from the output layer all the way back to the input layer. The backward locking in backpropagation algorithm constrains us from updating network layers in parallel and fully l…

A new model decouples global and local image representations without supervision.

Decoupled PFNs improve sequential decision-making by separating epistemic and aleatoric uncertainties.

Novel Adam-family method with decoupled weight decay for training neural networks.

DAPS++ improves diffusion-based image restoration by decoupling prior and likelihood.

New method uses diffusion models for Bayesian inverse problems.

We investigate the convergence and stability properties of the decoupled extended Kalman filter learning algorithm (DEKF) within the long-short term memory network (LSTM) based online learning framework. For this purpose, we model DEKF as a perturbed extended Kalman filter and derive sufficient conditions for its stabi…

DAPS++ improves diffusion-based image restoration by decoupling prior and likelihood.

FTPL policy achieves best-of-both-worlds regret in decoupled bandits with reduced computational cost.

New method detects heuristics in complex game strategies.

Study compares constrained and decoupled moduli spaces of manifolds with particles and discs.

Unsupervised representation learning via generative modeling is a staple to many computer vision applications in the absence of labeled data. Variational Autoencoders (VAEs) are powerful generative models that learn representations useful for data generation. However, due to inherent challenges in the training objectiv…

The paper extends macroscopic market making to stochastic games, revealing properties and solving equations.

Tech sector decouples from non-tech sectors post-2015, predicting economic growth.

A new loss function HUG decouples and generalizes neural collapse.

A new method for faster multi-objective optimization by evaluating objectives separately.

The study extends Jacobi-orthogonality to indefinite scalar product spaces.

New characterization of Osserman tensors using Jacobi-orthogonality.