Related papers: Accelerating Derivative-Free Optimization with Dim…

Spatial frequency estimation from a mixture of noisy sinusoids finds applications in various fields. While subspace-based methods offer cost-effective super-resolution parameter estimation, they demand precise array calibration, posing…

Massive datasets often contain redundancy that inflates computational costs without improving generalization. Existing data reduction methods are typically task-agnostic, discarding informative boundary samples and yielding suboptimal…

Many signal processing applications such as acoustic echo cancellation and wireless channel estimation require identifying systems where only a small fraction of coefficients are actually active, i.e. sparse systems. Zero-attracting…

When simulating multiscale stochastic differential equations (SDEs) in high-dimensions, separation of timescales, stochastic noise and high-dimensionality can make simulations prohibitively expensive. The computational cost is dictated by…

The growing use of information hiding in network streaming media for covert communication poses a significant security threat, necessitating the development of robust detection technologies. However, existing steganalysis methods for…

The high-dimensional rank lasso (hdr lasso) model is an efficient approach to deal with high-dimensional data analysis. It was proposed as a tuning-free robust approach for the high-dimensional regression and was demonstrated to enjoy…

Unsupervised domain adaption has been widely adopted in tasks with scarce annotated data. Unfortunately, mapping the target-domain distribution to the source-domain unconditionally may distort the essential structural information of the…

Adapting pre-trained models with broad capabilities has become standard practice for learning a wide range of downstream tasks. The typical approach of fine-tuning different models for each task is performant, but incurs a substantial…

Differentiable Neural Architecture Search (NAS) provides efficient, gradient-based methods for automatically designing neural networks, yet its adoption remains limited in practice. We present MIDAS, a novel approach that modernizes DARTS…

It is well known that we need to choose the hyper-parameters in Momentum, AdaGrad, AdaDelta, and other alternative stochastic optimizers. While in many cases, the hyper-parameters are tuned tediously based on experience becoming more of an…

In this paper, we consider reinforcement learning of nonlinear systems with continuous state and action spaces. We present an episodic learning algorithm, where we for each episode use convex optimization to find a two-layer neural network…

The sparse-group lasso performs both variable and group selection, simultaneously using the strengths of the lasso and group lasso. It has found widespread use in genetics, a field that regularly involves the analysis of high-dimensional…

Modern retrieval systems increasingly require integrating approximate nearest neighbor search (ANNS) with complex attribute filtering to handle hybrid queries in applications such as recommendation systems and retrieval-augmented generation…

Recent methods for long-tailed instance segmentation still struggle on rare object classes with few training data. We propose a simple yet effective method, Feature Augmentation and Sampling Adaptation (FASA), that addresses the data…

The use of derivative-based solvers to compute solutions to optimal control problems with non-differentiable cost or dynamics often requires reformulations or relaxations that complicate the implementation or increase computational…

We propose an Adagrad-like algorithm for multi-objective unconstrained optimization that relies on the computation of a common descent direction only. Unlike classical local algorithms for multi-objective optimization, our approach does not…

Deep neural networks have emerged as powerful tools for learning operators defined over infinite-dimensional function spaces. However, existing theories frequently encounter difficulties related to dimensionality and limited…

We present STaR, a novel method that performs Self-supervised Tracking and Reconstruction of dynamic scenes with rigid motion from multi-view RGB videos without any manual annotation. Recent work has shown that neural networks are…

Unsupervised machine learning methods are well suited to searching for anomalies at scale but can struggle with the high-dimensional representation of many modern datasets, hence dimensionality reduction (DR) is often performed first. In…

Aiming at improving performance of visual classification in a cost-effective manner, this paper proposes an incremental semi-supervised learning paradigm called Deep Co-Space (DCS). Unlike many conventional semi-supervised learning methods…