Related papers: Gradient-Adaptive Spline-Interpolated LUT Methods …

Structured pruning reduces LLM inference cost by removing low-importance architectural components. This can be viewed as learning a multiplicative gate for each component under an l0 sparsity constraint. Due to the discreteness of the l0…

Recent Deep Unfolding Networks (DUNs) have significantly advanced Compressive Sensing (CS) by integrating iterative optimization with deep networks. However, existing DUNs still suffer from two challenges: 1) Reliance on a single…

Low-rank adaptation (LoRA) has been demonstrated effective in reducing the trainable parameter number when fine-tuning a large foundation model (LLM). However, it still encounters computational and memory challenges when scaling to larger…

This paper investigates the use of Neural Network (NN) nonlinear modelling for Power Amplifier (PA) linearization in the Walsh-Hadamard transceiver architecture. This novel architecture has recently been proposed for ultra-high bandwidth…

This paper introduces a low-complexity memoryless linearizer for suppression of distortion in analog-to-digital interfaces. It is inspired by neural networks, but has a substantially lower complexity than the neural-network schemes that…

DSP (digital signal processing) has been widely applied in optical communication systems to mitigate signal distortions and has become one of the key technologies that have sustained data traffic growth over the past decade. However, the…

Sharpness-aware Minimization (SAM) has been proposed recently to improve model generalization ability. However, SAM calculates the gradient twice in each optimization step, thereby doubling the computation costs compared to stochastic…

In real-world applications, it is important for machine learning algorithms to be robust against data outliers or corruptions. In this paper, we focus on improving the robustness of a large class of learning algorithms that are formulated…

In this paper, we introduce proximal gradient temporal difference learning, which provides a principled way of designing and analyzing true stochastic gradient temporal difference learning algorithms. We show how gradient TD (GTD)…

We introduce a framework for linear precoder design over a massive multiple-input multiple-output downlink system in the presence of nonlinear power amplifiers (PAs). By studying the spatial characteristics of the distortion, we demonstrate…

Linear and nonlinear distortions in optical communication signals are equalized using an integrated feed-forward Photonic Neural Network (PNN). The PNN is based on a linear stage made of an 8-tap Finite Impulse Response (FIR) filter,…

A large majority of cellular networks deployed today make use of Frequency Division Duplexing (FDD) where, in contrast with Time Division Duplexing (TDD), the channel reciprocity does not hold and explicit downlink (DL) probing and uplink…

Structured pruning can simplify network architecture and improve inference speed. Combined with the underlying hardware and inference engine in which the final model is deployed, better results can be obtained by using latency collaborative…

In this paper, we study FPGA based pipelined and superscalar design of two variants of conjugate gradient methods for solving Laplacian equation on a discrete grid; the first version corresponds to the original conjugate gradient algorithm,…

Gaussian processes (GPs) stand as crucial tools in machine learning and signal processing, with their effectiveness hinging on kernel design and hyper-parameter optimization. This paper presents a novel GP linear multiple kernel (LMK) and a…

In frequency-division duplex (FDD) massive multiple-input multiple-output (MIMO) systems, the growing number of base station antennas leads to prohibitive feedback overhead for downlink channel state information (CSI). To address this…

Differentially private (DP) image synthesis generates images that preserve the statistical characteristics of a sensitive dataset, enabling sensitive data analysis and usage while providing rigorous guarantees of privacy leakage. Existing…

Unsupervised domain adaptation (UDA) for semantic segmentation aims to adapt a segmentation model trained on the labeled source domain to the unlabeled target domain. Existing methods try to learn domain invariant features while suffering…

We consider the problem of how to reduce the cost of communication that is required for the parallel training of a neural network. The state-of-the-art method, Bulk Synchronous Parallel Stochastic Gradient Descent (BSP-SGD), requires many…

Massive multiple-input multiple-output (mMIMO) downlink precoding offers high spectral efficiency but remains challenging to deploy in practice because near-optimal algorithms such as the weighted minimum mean squared error (WMMSE) are…