Related papers: Bridging the Initialization Gap: A Co-Optimization…
Parameter-efficient fine-tuning (PEFT) is a standard way to adapt multimodal large language models, yet extremely low-rank settings -- especially rank-1 LoRA -- are often unstable. We show that this instability is not solely due to limited…
Heuristic optimisers which search for an optimal configuration of variables relative to an objective function often get stuck in local optima where the algorithm is unable to find further improvement. The standard approach to circumvent…
The optimization of porous infill structures via local volume constraints has become a popular approach in topology optimization. In some design settings, however, the iterative optimization process converges only slowly, or not at all even…
This paper addresses the problem of localizing change points in high-dimensional linear regression models with piecewise constant regression coefficients. We develop a dynamic programming approach to estimate the locations of the change…
In this investigation, we propose several algorithms to recover the location and intensity of a radiation source located in a simulated 250 m x 180 m block in an urban center based on synthetic measurements. Radioactive decay and detection…
Reconfigurable intelligent surfaces (RISs) have tremendous potential to boost communication performance, especially when the line-of-sight (LOS) path between the user equipment (UE) and base station (BS) is blocked. To control the RIS,…
While deploying large language models on edge devices promises low-latency and privacy-preserving AI services, it is hindered by limited device resources. Although pipeline parallelism facilitates distributed inference, existing approaches…
Pre-training is essential to deep learning model performance, especially in medical image analysis tasks where limited training data are available. However, existing pre-training methods are inflexible as the pre-trained weights of one…
A critical challenge of federated learning is data heterogeneity and imbalance across clients, which leads to inconsistency between local networks and unstable convergence of global models. To alleviate the limitations, we propose a novel…
Neural networks trained via gradient descent with random initialization and without any regularization enjoy good generalization performance in practice despite being highly overparametrized. A promising direction to explain this phenomenon…
We present a novel path-planning algorithm to reduce localization error for a network of robots cooperatively localizing via inter-robot range measurements. The quality of localization with range measurements depends on the configuration of…
Appropriate weight initialization has been of key importance to successfully train neural networks. Recently, batch normalization has diminished the role of weight initialization by simply normalizing each layer based on batch statistics.…
The discretization of constrained nonlinear optimization problems arising in the field of topology optimization yields algebraic systems which are challenging to solve in practice, due to pathological ill-conditioning, strong nonlinearity…
Resource allocation with quality of service constraints is one of the most challenging problems in elastic optical networks which is normally formulated as an MINLP optimization program. In this paper, we focus on novel properties of…
Indoor localization is critical for IoT applications, yet challenges such as non-Gaussian noise, environmental interference, and measurement outliers hinder the robustness of traditional methods. Existing approaches, including Kalman…
Motivated by the emerging role of interpolating machines in signal processing and machine learning, this work considers the computational aspects of over-parametrized matrix factorization. In this context, the optimization landscape may…
High-level synthesis, source-to-source compilers, and various Design Space Exploration techniques for pragma insertion have significantly improved the Quality of Results of generated designs. These tools offer benefits such as reduced…
Mixed-precision quantization (MPQ) is crucial for deploying deep neural networks on resource-constrained devices, but finding the optimal bit-width for each layer represents a complex combinatorial optimization problem. Current…
Initialization is essential to monocular Simultaneous Localization and Mapping (SLAM) problems. This paper focuses on a novel initialization method for monocular SLAM based on planar features. The algorithm starts by homography estimation…
Large-scale place recognition is a fundamental but challenging task, which plays an increasingly important role in autonomous driving and robotics. Existing methods have achieved acceptable good performance, however, most of them are…