相关论文: Machine learning-based EDFA Gain Model Generalizab…

We present a novel end-to-end autoencoder-based learning for coherent optical communications using a "parallelizable" perturbative channel model. We jointly optimized constellation shaping and nonlinear pre-emphasis achieving mutual…

Weight averaging of Stochastic Gradient Descent (SGD) iterates is a popular method for training deep learning models. While it is often used as part of complex training pipelines to improve generalization or serve as a `teacher' model,…

The joint training of speech enhancement and speaker embedding networks for speaker recognition is widely adopted under noisy acoustic environments. While effective, this paradigm often fails to leverage the generalization and robustness…

In this paper, we propose an Expectation-Maximization-based (EM) Personalized Federated Learning (PFL) framework for multi-objective optimization (MOO) in Integrated Sensing and Communication (ISAC) systems. In contrast to standard…

This work focuses on improving the performance and fairness of Federated Learning (FL) in non IID settings by enhancing model aggregation and boosting the training of underperforming clients. We propose FeDABoost, a novel FL framework that…

Deploying speech enhancement (SE) systems in wearable devices, such as smart glasses, is challenging due to the limited computational resources on the device. Although deep learning methods have achieved high-quality results, their…

Recent Deep Neural Networks (DNN) applications ask for techniques that can explain their behavior. Existing solutions, such as Feature Guided Analysis (FGA), extract rules on their internal behaviors, e.g., by providing explanations related…

Traditional spectral energy distribution (SED) fitting techniques face uncertainties due to assumptions in star formation histories and dust attenuation curves. We propose an advanced machine learning-based approach that enhances…

We provide a theoretical analysis for end-to-end training Discrete Flow Matching (DFM) generative models. DFM is a promising discrete generative modeling framework that learns the underlying generative dynamics by training a neural network…

In this work we use a micromechanical resonator to experimentally study small signal amplification near the onset of Duffing bistability. The device consists of a PdAu beam serving as a micromechanical resonator excited by an adjacent gate…

We obtain a denoising loss bound of the recently proposed neural network based universal discrete denoiser, Neural DUDE, which can adaptively learn its parameters solely from the noise-corrupted data, by minimizing the \emph{empirical…

A new method for measuring the linewidth enhancement factor of a laser is proposed. It is based on frequency-modulated optical injection, combined with dual-frequency laser operation. The linewidth enhancement factor {\alpha} is deduced…

We propose an audio effects processing framework that learns to emulate a target electric guitar tone from a recording. We train a deep neural network using an adversarial approach, with the goal of transforming the timbre of a guitar, into…

We present an impedance engineered Josephson parametric amplifier capable of providing bandwidth beyond the traditional gain-bandwidth product. We achieve this by introducing a positive linear slope in the imaginary component of the input…

We explore a data-driven approach for learning to optimize neural networks. We construct a dataset of neural network checkpoints and train a generative model on the parameters. In particular, our model is a conditional diffusion transformer…

Multimedia recommender systems focus on utilizing behavioral information and content information to model user preferences. Typically, it employs pre-trained feature encoders to extract content features, then fuses them with behavioral…

Deep Neural Networks are well known for efficiently fitting training data, yet experiencing poor generalization capabilities whenever some kind of bias dominates over the actual task labels, resulting in models learning "shortcuts". In…

Federated edge learning (FEEL) is a framework for training models in a distributed fashion using edge devices and a server that coordinates the learning process. In FEEL, edge devices periodically transmit model parameters to the server,…

Dependence of mode instabilities (MI) on ytterbium dopant concentrations in high power fiber amplifiers has been investigated. It is theoretically shown that, by only varying the fiber length to maintain the same total small-signal pump…

Audio diffusion models can synthesize a wide variety of sounds. Existing models often operate on the latent domain with cascaded phase recovery modules to reconstruct waveform. This poses challenges when generating high-fidelity audio. In…