Zobrazeno 1 - 10
of 258
pro vyhledávání: '"Nowak, Robert D"'
Autor:
Yang, Liu, Paischer, Fabian, Hassani, Kaveh, Li, Jiacheng, Shao, Shuai, Li, Zhang Gabriel, He, Yun, Feng, Xue, Noorshams, Nima, Park, Sem, Long, Bo, Nowak, Robert D, Gao, Xiaoli, Eghbalzadeh, Hamid
Sequential dense retrieval models utilize advanced sequence learning techniques to compute item and user representations, which are then used to rank relevant items for a user through inner product computation between the user and all item representa
Externí odkaz:
http://arxiv.org/abs/2411.18814
This paper studies the properties of solutions to multi-task shallow ReLU neural network learning problems, wherein the network is trained to fit a dataset with minimal sum of squared weights. Remarkably, the solutions learned for each individual tas
Externí odkaz:
http://arxiv.org/abs/2410.21696
Motivated by the growing theoretical understanding of neural networks that employ the Rectified Linear Unit (ReLU) as their activation function, we revisit the use of ReLU activation functions for learning implicit neural representations (INRs). Insp
Externí odkaz:
http://arxiv.org/abs/2406.02529
Autor:
Bhatt, Gantavya, Chen, Yifang, Das, Arnav M., Zhang, Jifan, Truong, Sang T., Mussmann, Stephen, Zhu, Yinglun, Bilmes, Jeffrey, Du, Simon S., Jamieson, Kevin, Ash, Jordan T., Nowak, Robert D.
Supervised finetuning (SFT) on instruction datasets has played a crucial role in achieving the remarkable zero-shot generalization capabilities observed in modern large language models (LLMs). However, the annotation efforts required to produce high
Externí odkaz:
http://arxiv.org/abs/2401.06692
Publikováno v:
Applied and Computational Harmonic Analysis, vol. 74, no. 101713, pp. 1-22, 2025
We investigate the approximation of functions $f$ on a bounded domain $\Omega\subset \mathbb{R}^d$ by the outputs of single-hidden-layer ReLU neural networks of width $n$. This form of nonlinear $n$-term dictionary approximation has been intensely st
Externí odkaz:
http://arxiv.org/abs/2307.15772
Autor:
Zhang, Jifan, Chen, Yifang, Canal, Gregory, Mussmann, Stephen, Das, Arnav M., Bhatt, Gantavya, Zhu, Yinglun, Bilmes, Jeffrey, Du, Simon Shaolei, Jamieson, Kevin, Nowak, Robert D
Labeled data are critical to modern machine learning applications, but obtaining labels can be expensive. To mitigate this cost, machine learning methods, such as transfer learning, semi-supervised learning and active learning, aim to be label-effici
Externí odkaz:
http://arxiv.org/abs/2306.09910
Publikováno v:
Journal of Machine Learning Research, vol. 25, no. 231, pp. 1-40, 2024
This paper introduces a novel theoretical framework for the analysis of vector-valued neural networks through the development of vector-valued variation spaces, a new class of reproducing kernel Banach spaces. These spaces emerge from studying the re
Externí odkaz:
http://arxiv.org/abs/2305.16534
Iterative denoising algorithms (IDAs) have been tremendously successful in a range of linear inverse problems arising in signal and image processing. The classic instance of this is the famous Iterative Soft-Thresholding Algorithm (ISTA), based on so
Externí odkaz:
http://arxiv.org/abs/2302.07972
Autor:
Parhi, Rahul, Nowak, Robert D.
Publikováno v:
IEEE Signal Processing Magazine, vol. 40, no. 6, pp. 63-74, Sept. 2023
Deep learning has been wildly successful in practice and most state-of-the-art machine learning methods are based on neural networks. Lacking, however, is a rigorous mathematical theory that adequately explains the amazing performance of deep neural
Externí odkaz:
http://arxiv.org/abs/2301.09554
Autor:
Yang, Liu, Zhang, Jifan, Shenouda, Joseph, Papailiopoulos, Dimitris, Lee, Kangwook, Nowak, Robert D.
Weight decay is one of the most widely used forms of regularization in deep learning, and has been shown to improve generalization and robustness. The optimization objective driving weight decay is a sum of losses plus a term proportional to the sum
Externí odkaz:
http://arxiv.org/abs/2210.03069