1 code implementation • 20 Dec 2023 • Yilang Zhang, Bingcong Li, Georgios B. Giannakis
Utilizing task-invariant prior knowledge extracted from related tasks, meta-learning is a principled framework that empowers learning a new task especially when data records are limited.
no code implementations • 13 Dec 2023 • Bingcong Li, Shuai Zheng, Parameswaran Raman, Anshumali Shrivastava, Georgios B. Giannakis
On-device memory concerns in distributed deep learning have become severe due to (i) the growth of model size in multi-GPU training, and (ii) the wide adoption of deep neural networks for federated learning on IoT devices which have limited storage.
no code implementations • 14 Oct 2023 • Liang Zhang, Bingcong Li, Kiran Koshy Thekumparampil, Sewoong Oh, Niao He
The widespread practice of fine-tuning large language models (LLMs) on domain-specific data faces two major challenges in memory and privacy.
1 code implementation • NeurIPS 2023 • Bingcong Li, Georgios B. Giannakis
Sharpness-aware minimization (SAM) has well documented merits in enhancing generalization of deep neural networks, even without sizable data augmentation.
no code implementations • 13 Aug 2023 • Bingcong Li, Georgios B. Giannakis
Conic programming has well-documented merits in a gamut of signal processing and machine learning tasks.
1 code implementation • 31 Mar 2023 • Yilang Zhang, Bingcong Li, Shijian Gao, Georgios B. Giannakis
Meta-learning owns unique effectiveness and swiftness in tackling emerging tasks with limited data.
no code implementations • 27 May 2022 • Qin Lu, Konstantinos D. Polyzos, Bingcong Li, Georgios B. Giannakis
Tests on synthetic functions and real-world applications showcase the merits of the proposed method.
no code implementations • 20 Oct 2021 • Alireza Sadeghi, Meng Ma, Bingcong Li, Georgios B. Giannakis
The data distribution is considered unknown, but lies within a Wasserstein ball centered around empirical data distribution.
no code implementations • NeurIPS 2021 • Bingcong Li, Alireza Sadeghi, Georgios B. Giannakis
Conditional gradient, aka Frank Wolfe (FW) algorithms, have well-documented merits in machine learning and signal processing applications.
no code implementations • 5 May 2021 • Yelin He, Xianbiao Qi, Jiaquan Ye, Peng Gao, Yihao Chen, Bingcong Li, Xin Tang, Rong Xiao
This paper presents our solution for the ICDAR 2021 Competition on Scientific Table Image Recognition to LaTeX.
no code implementations • 10 Dec 2020 • Lingda Wang, Bingcong Li, Huozhi Zhou, Georgios B. Giannakis, Lav R. Varshney, Zhizhen Zhao
The second algorithm, \texttt{EXP3-LGC-IX}, is developed for a special class of problems, for which the regret is reduced to $\mathcal{O}(\sqrt{\alpha(G)dT\log{K}\log(KT)})$ for both directed as well as undirected feedback graphs.
no code implementations • 9 Dec 2020 • Bingcong Li, Lingda Wang, Georgios B. Giannakis, Zhizhen Zhao
Relying on no problem dependent parameters in the step sizes, the convergence rate of ExtraFW for general convex problems is shown to be ${\cal O}(\frac{1}{k})$, which is optimal in the sense of matching the lower bound on the number of solved FW subproblems.
no code implementations • 6 Nov 2020 • Bingcong Li, Bo Han, Zhuowei Wang, Jing Jiang, Guodong Long
Specifically, our method maintains a dynamically updating confusion matrix, which analyzes confusable classes in the dataset.
no code implementations • 23 Sep 2020 • Bingcong Li, Xin Tang, Xianbiao Qi, Yihao Chen, Rong Xiao
Thus, we propose a lightweight scene text recognition model named Hamming OCR.
no code implementations • 19 Jun 2020 • Bingcong Li, Mario Coutino, Georgios B. Giannakis, Geert Leus
We unveil the connections between Frank Wolfe (FW) type algorithms and the momentum in Accelerated Gradient Methods (AGM).
no code implementations • 15 Oct 2019 • Bingcong Li, Georgios B. Giannakis
The main goal of this work is equipping convex and nonconvex problems with Barzilai-Borwein (BB) step size.
no code implementations • 12 Sep 2019 • Lingda Wang, Huozhi Zhou, Bingcong Li, Lav R. Varshney, Zhizhen Zhao
Cascading bandit (CB) is a popular model for web search and online advertising, where an agent aims to learn the $K$ most attractive items out of a ground set of size $L$ during the interaction with a user.
no code implementations • 10 Sep 2019 • Gang Wang, Bingcong Li, Georgios B. Giannakis
Motivated by the widespread use of temporal-difference (TD-) and Q-learning algorithms in reinforcement learning, this paper studies a class of biased stochastic approximation (SA) procedures under a mild "ergodic-like" assumption on the underlying stochastic noise sequence.
no code implementations • ICML 2020 • Bingcong Li, Lingda Wang, Georgios B. Giannakis
Then a simple yet effective means to adjust the number of iterations per inner loop is developed to enhance the merits of the proposed averaging schemes and BB step sizes.
no code implementations • 5 Jun 2019 • Bingcong Li, Meng Ma, Georgios B. Giannakis
For convex problems, when adopting an $n$-dependent step size, the complexity of L2S is ${\cal O}(n+ \sqrt{n}/\epsilon)$; while for more frequently adopted $n$-independent step size, the complexity is ${\cal O}(n+ n/\epsilon)$.
no code implementations • 29 Jan 2019 • Miao Xu, Bingcong Li, Gang Niu, Bo Han, Masashi Sugiyama
May there be a new sample selection method that can outperform the latest importance reweighting method in the deep learning age?
no code implementations • 9 Jul 2018 • Bingcong Li, Tianyi Chen, Georgios B. Giannakis
This paper deals with bandit online learning problems involving feedback of unknown delay that can emerge in multi-armed bandit (MAB) and bandit convex optimization (BCO) settings.
no code implementations • 9 May 2018 • Bingcong Li, Tianyi Chen, Georgios B. Giannakis
To accommodate heterogeneous tasks in Internet of Things (IoT), a new communication and computing paradigm termed mobile edge computing emerges that extends computing services from the cloud to edge, but at the same time exposes new challenges on security.