arXiv research

SSL framework identifies non-linear systems without labeled data.

Study on dynamics of non-linear autoencoders learning principal components.

Machine learning improves joint default assessment by capturing non-linear dependencies.

Optimal algorithms for non-linear ridge bandits reduce burn-in cost.

SAFLe solves federated learning's trade-off between non-linearity and scalability.

Gradient descent with growing learning rate enables learning non-linear features in neural networks.

Traditional linear methods for forecasting multivariate time series are not able to satisfactorily model the non-linear dependencies that may exist in non-Gaussian series. We build on the theory of learning vector-valued functions in the reproducing kernel Hilbert space and develop a method for learning prediction func…

New classifier combines locally linear kernels for fast and accurate non-linear classification.

This paper studies the dynamic generator model for spatial-temporal processes such as dynamic textures and action sequences in video data. In this model, each time frame of the video sequence is generated by a generator model, which is a non-linear transformation of a latent state vector, where the non-linear transform…

We study a non-linear statistical inverse learning problem, where we observe the noisy image of a quantity through a non-linear operator at some random design points. We consider the widely used Tikhonov regularization (or method of regularization, MOR) approach to reconstruct the estimator of the quantity for the non-…

ENIAC method optimizes and explores complex RL problems with non-linear policies.

DPLS improves asset pricing by capturing non-linear risk factor structures.

Paper proposes a bias-constrained deep learning approach to non-linear estimation.

New models learn stable latent clusters without side info.

We develop algorithms to learn non-linear dynamical systems without mixing assumptions.

Unified framework for non-linear attention using modern Hopfield networks.

Agents learn state ambiguity from non-linear sensor data using Gaussian approximations.

Enhances Cox model for survival analysis with symbolic non-linear log-risk functions.

This paper proposes a new method to learn integration schemes for complex ODEs.

New method for interpreting non-linear models using forward marginal effects.

This research evaluates learning models for bionic robots, focusing on transfer function identification.

This paper conditions non-linear infinite-dimensional diffusion processes.

Develops inverse EKF for non-linear systems with stability guarantees and learning unknown dynamics.

Paper introduces non-linearity signature to measure deep neural network performance.

Develops deep learning methods for non-linear PDEs in credit risk.

Study reward-free RL in non-linear settings, improving efficiency and removing assumptions.

Simplifies deep learning scaling analysis without sacrificing accuracy.

New neural network models for functional data.

Papers learn from data to make decisions without interacting, improving on previous methods.

Complex problems may require sophisticated, non-linear learning methods such as kernel machines or deep neural networks to achieve state of the art prediction accuracies. However, high prediction accuracies are not the only objective to consider when solving problems using machine learning. Instead, particular scientif…

Learning weights in a spiking neural network with hidden neurons, using local, stable and online rules, to control non-linear body dynamics is an open problem. Here, we employ a supervised scheme, Feedback-based Online Local Learning Of Weights (FOLLOW), to train a network of heterogeneous spiking neurons with hidden l…

Deep networks prioritize easier examples over harder ones, leading to faster training.

A semi-parametric, non-linear regression model in the presence of latent variables is applied towards learning network graph structure. These latent variables can correspond to unmodeled phenomena or unmeasured agents in a complex system of interacting entities. This formulation jointly estimates non-linearities in the…

New Shapley values reveal non-linear feature dependencies.

Improved regret bound for multinomial logistic bandits with non-linearity.

We present a multi-task learning formulation for Deep Gaussian processes (DGPs), through non-linear mixtures of latent processes. The latent space is composed of private processes that capture within-task information and shared processes that capture across-task dependencies. We propose two different methods for segmen…

New method adds all interactions in non-linear models without high computational cost.

We present a general framework for solving a large class of learning problems with non-linear functions of classification rates. This includes problems where one wishes to optimize a non-decomposable performance metric such as the F-measure or G-mean, and constrained training problems where the classifier needs to sati…

Neural networks with at least two hidden layers are called deep networks. Recent developments in AI and computer programming in general has led to development of tools such as Tensorflow, Keras, NumPy etc. making it easier to model and draw conclusions from data. In this work we re-approach non-linear regression with d…

Machine learning algorithms are typically run on large scale, distributed compute infrastructure that routinely face a number of unavailabilities such as failures and temporary slowdowns. Adding redundant computations using coding-theoretic tools called "codes" is an emerging technique to alleviate the adverse effects …

Analyzes generalization error in generalized linear models, explaining double descent phenomenon.

A new method learns state and proposal dynamics in state-space models using neural networks.

Modeling dynamical systems is important in many disciplines, e.g., control, robotics, or neurotechnology. Commonly the state of these systems is not directly observed, but only available through noisy and potentially high-dimensional observations. In these cases, system identification, i.e., finding the measurement map…

We propose a new Bayesian tracking and parameter learning algorithm for non-linear non-Gaussian multiple target tracking (MTT) models. We design a Markov chain Monte Carlo (MCMC) algorithm to sample from the posterior distribution of the target states, birth and death times, and association of observations to targets, …

A basic problem in machine learning is to find a mapping $f$ from a low dimensional latent space $\mathcal{Y}$ to a high dimensional observation space $\mathcal{X}$. Modern tools such as deep neural networks are capable to represent general non-linear mappings. A learner can easily find a mapping which perfectly fits a…

The success of deep learning is due, to a large extent, to the remarkable effectiveness of gradient-based optimization methods applied to large neural networks. The purpose of this work is to propose a modern view and a general mathematical framework for loss landscapes and efficient optimization in over-parameterized …

Active learning selects inputs for GPSSM to learn latent states.

Develops a Riemannian archetypal analysis for interpretable non-linear data.