arXiv research

Paper proposes active learning for structured output design, improving Gaussian process model predictions.

DeepICMGP surrogate models multiple outputs efficiently.

Approach uses machine learning to identify structural modal parameters from output-only data.

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

Structural optimization is a popular method for designing objects such as bridge trusses, airplane wings, and optical devices. Unfortunately, the quality of solutions depends heavily on how the problem is parameterized. In this paper, we propose using the implicit bias over functions induced by neural networks to impro…

Safe neural networks for input-output specifications.

We propose and analyze a regularization approach for structured prediction problems. We characterize a large class of loss functions that allows to naturally embed structured outputs in a linear space. We exploit this fact to design learning algorithms using a surrogate loss approach and regularization techniques. We p…

A new framework learns differentiable structured losses from data.

Paper designs optimal ECOCs using IP for robust multiclass classification.

A computer code can simulate a system's propagation of variation from random inputs to output measures of quality. Our aim here is to estimate a critical output tail probability or quantile without a large Monte Carlo experiment. Instead, we build a statistical surrogate for the input-output relationship with a modest …

We study the interplay between surrogate methods for structured prediction and techniques from multitask learning designed to leverage relationships between surrogate outputs. We propose an efficient algorithm based on trace norm regularization which, differently from previous methods, does not require explicit knowled…

DeepJSCC-f uses feedback to improve image transmission quality.

DiffDenoise preserves fine structures in medical images using conditional diffusion models.

New algorithms handle online prediction with bandit and delayed feedback, improving regret bounds.

For many important problems the quantity of interest is an unknown function of the parameters, which is a random vector with known statistics. Since the dependence of the output on this random vector is unknown, the challenge is to identify its statistics, using the minimum number of function evaluations. This problem …

Optimal algorithms identify non-dominated arms in multi-output linear bandit models.

SpodNet learns SPD matrices with structural constraints.

In this paper we consider Multiple-Input-Multiple-Output (MIMO) detection using deep neural networks. We introduce two different deep architectures: a standard fully connected multi-layer network, and a Detection Network (DetNet) which is specifically designed for the task. The structure of DetNet is obtained by unfold…

Paper proposes a self-training method to generate molecular targets.

We provide a methodology, resilient feature engineering, for creating adversarially resilient classifiers. According to existing work, adversarial attacks identify weakly correlated or non-predictive features learned by the classifier during training and design the adversarial noise to utilize these features. Therefore…

A new method reduces both input and output dimensions for better goal-oriented analysis.

New method learns output embeddings for structured prediction.

Bayesian-guided method selects optimal design from large candidate pool.

Improves Bayesian optimisation for engineering design problems with many variables.

Study of online learning for structured prediction problems.

Surrogate model construction for vector-valued outputs

Improved investment performance with fine-grained LLM tasks.

The demand for fast and accurate structural analysis is becoming increasingly more prevalent with the advance of generative design and topology optimization technologies. As one step toward accelerating structural analysis, this work explores a deep learning based approach for predicting the stress fields in 2D linear …

Bayesian optimization of function networks using intermediate outputs.

Improved code translation by preserving structure with composed fine-tuning.

New method certifies risks of LLM outputs, improving accuracy and reliability.

EBM predicts protein conformations at atomic scale using crystallized data.

A method for predicting signals on graphs using Gaussian processes and optimal transport.

New MIMO constellation design for noncoherent communications reduces hardware complexity.

PASCO speeds up graph clustering for large graphs.

We study the problem of structured output learning from a regression perspective. We first provide a general formulation of the kernel dependency estimation (KDE) problem using operator-valued kernels. We show that some of the existing formulations of this problem are special cases of our framework. We then propose a c…

Develops nonstationary MOGP kernels for better performance.

Kernel methods are among the most popular techniques in machine learning. From a frequentist/discriminative perspective they play a central role in regularization theory as they provide a natural choice for the hypotheses space and the regularization functional through the notion of reproducing kernel Hilbert spaces. F…

Scene text magnifier aims to magnify text in natural scene images without recognition. It could help the special groups, who have myopia or dyslexia to better understand the scene. In this paper, we design the scene text magnifier through interacted four CNN-based networks: character erasing, character extraction, char…

Introduces foundation priors for using model-generated data in empirical research.

Optimizes hydrokinetic turbine design using morphing and Bayesian optimization.

Proposes SHORE model for efficient MOR with sparsity and scalability.

Conditional Restricted Boltzmann Machines (CRBMs) are rich probabilistic models that have recently been applied to a wide range of problems, including collaborative filtering, classification, and modeling motion capture data. While much progress has been made in training non-conditional RBMs, these algorithms are not a…

Graph-to-Tree Neural Networks improve structured input-output translation in tasks like semantic parsing and math word problems.

We propose a new algorithm to learn a one-hidden-layer convolutional neural network where both the convolutional weights and the outputs weights are parameters to be learned. Our algorithm works for a general class of (potentially overlapping) patches, including commonly used structures for computer vision tasks. Our a…

A deep convolutional fuzzy system (DCFS) on a high-dimensional input space is a multi-layer connection of many low-dimensional fuzzy systems, where the input variables to the low-dimensional fuzzy systems are selected through a moving window across the input spaces of the layers. To design the DCFS based on input-outpu…

Study efficient interactive learning for structured outputs with reliable computation.

The study addresses negative transfer in multi-output Gaussian processes by proposing latent structures.