no code implementations • ICML 2020 • Daniel Rothchild, Ashwinee Panda, Enayat Ullah, Nikita Ivkin, Vladimir Braverman, Joseph Gonzalez, Ion Stoica, Raman Arora

A key insight in the design of FedSketchedSGD is that, because the Count Sketch is linear, momentum and error accumulation can both be carried out within the sketch.

no code implementations • 15 Aug 2024 • Guanchu Wang, Junhao Ran, Ruixiang Tang, Chia-Yuan Chang, Yu-Neng Chuang, Zirui Liu, Vladimir Braverman, Zhandong Liu, Xia Hu

In this work, we introduce a rare disease question-answering (ReDis-QA) dataset to evaluate the performance of LLMs in diagnosing rare diseases.

no code implementations • 16 Jul 2024 • Vladimir Braverman, Prathamesh Dharangutte, Vihan Shah, Chen Wang

The MIS problem is known to be NP-hard and is also NP-hard to approximate to within a factor of $n^{1-\delta}$ for any $\delta>0$.

1 code implementation • 5 Feb 2024 • Zirui Liu, Jiayi Yuan, Hongye Jin, Shaochen Zhong, Zhaozhuo Xu, Vladimir Braverman, Beidi Chen, Xia Hu

However, there is a lack of in-depth studies that explore the element distribution of KV cache to understand the hardness and limitation of KV cache quantization.

no code implementations • 20 Dec 2023 • Murad Tukan, Fares Fares, Yotam Grufinkle, Ido Talmor, Loay Mualem, Vladimir Braverman, Dan Feldman

In response to this formidable challenge, we introduce a real-time autonomous indoor exploration system tailored for drones equipped with a monocular \emph{RGB} camera.

no code implementations • 12 Oct 2023 • Jingfeng Wu, Difan Zou, Zixiang Chen, Vladimir Braverman, Quanquan Gu, Peter L. Bartlett

Transformers pretrained on diverse tasks exhibit remarkable in-context learning (ICL) capabilities, enabling them to solve unseen tasks solely based on input contexts without adjusting model parameters.

no code implementations • 11 Jul 2023 • Sanae Amani, Khushbu Pahwa, Vladimir Braverman, Lin F. Yang

Our research demonstrates that to achieve $\epsilon$-optimal policies for all $M$ tasks, a single agent using DistMT-LSVI needs to run a total number of episodes that is at most $\tilde{\mathcal{O}}({d^3H^6(\epsilon^{-2}+c_{\rm sep}^{-2})}\cdot M/N)$, where $c_{\rm sep}>0$ is a constant representing task separability, $H$ is the horizon of each episode, and $d$ is the feature dimension of the dynamics and rewards.

no code implementations • NeurIPS 2023 • Jingfeng Wu, Wennan Zhu, Peter Kairouz, Vladimir Braverman

For single-round FFE, it is known that count sketching is nearly information-theoretically optimal for achieving the fundamental accuracy-communication trade-offs [Chen et al., 2022].

no code implementations • 8 Jun 2023 • Guangyao Zheng, Shuhao Lai, Vladimir Braverman, Michael A. Jacobs, Vishwa S. Parekh

While Deep Reinforcement Learning has been widely researched in medical imaging, the training and deployment of these models usually require powerful GPUs.

no code implementations • 31 May 2023 • Guangyao Zheng, Shuhao Lai, Vladimir Braverman, Michael A. Jacobs, Vishwa S. Parekh

Deep reinforcement learning(DRL) is increasingly being explored in medical imaging.

1 code implementation • 19 May 2023 • Alaa Maalouf, Murad Tukan, Vladimir Braverman, Daniela Rus

A coreset is a tiny weighted subset of an input set, that closely resembles the loss function, with respect to a certain set of queries.

no code implementations • 17 Mar 2023 • Haoran Li, Jingfeng Wu, Vladimir Braverman

We consider a continual learning (CL) problem with two linear regression tasks in the fixed design setting, where the feature vectors are assumed fixed and the labels are assumed to be random variables.

no code implementations • 12 Mar 2023 • Guangyao Zheng, Michael A. Jacobs, Vladimir Braverman, Vishwa S. Parekh

Federated learning is a recent development in the machine learning area that allows a system of devices to train on one or more tasks without sharing their data to a single location or device.

1 code implementation • 9 Mar 2023 • Murad Tukan, Samson Zhou, Alaa Maalouf, Daniela Rus, Vladimir Braverman, Dan Feldman

In this paper, we introduce the first algorithm to construct coresets for \emph{RBFNNs}, i. e., small weighted subsets that approximate the loss of the input data on any radial basis function network and thus approximate any function defined by an \emph{RBFNN} on the larger input data.

no code implementations • 3 Mar 2023 • Jingfeng Wu, Difan Zou, Zixiang Chen, Vladimir Braverman, Quanquan Gu, Sham M. Kakade

On the other hand, we provide some negative results for stochastic gradient descent (SGD) for ReLU regression with symmetric Bernoulli data: if the model is well-specified, the excess risk of SGD is provably no better than that of GLM-tron ignoring constant factors, for each problem instance; and in the noiseless case, GLM-tron can achieve a small risk while SGD unavoidably suffers from a constant risk in expectation.

no code implementations • 22 Feb 2023 • Guangyao Zheng, Samson Zhou, Vladimir Braverman, Michael A. Jacobs, Vishwa S. Parekh

Selective experience replay aims to recount selected experiences from previous tasks to avoid catastrophic forgetting.

1 code implementation • 24 Sep 2022 • Ningyuan Huang, Soledad Villar, Carey E. Priebe, Da Zheng, Chengyue Huang, Lin Yang, Vladimir Braverman

Graph Neural Networks (GNNs) are powerful deep learning methods for Non-Euclidean data.

no code implementations • 3 Aug 2022 • Jingfeng Wu, Difan Zou, Vladimir Braverman, Quanquan Gu, Sham M. Kakade

Our bounds suggest that for a large class of linear regression instances, transfer learning with $O(N^2)$ source data (and scarce or no target data) is as effective as supervised learning with $N$ target data.

1 code implementation • NAACL 2022 • Orion Weller, Marc Marone, Vladimir Braverman, Dawn Lawrie, Benjamin Van Durme

Since the advent of Federated Learning (FL), research has applied these methods to natural language processing (NLP) tasks.

no code implementations • 12 Mar 2022 • Ali Abbasi, Parsa Nooralinejad, Vladimir Braverman, Hamed Pirsiavash, Soheil Kolouri

Overcoming catastrophic forgetting in deep neural networks has become an active field of research in recent years.

1 code implementation • 8 Mar 2022 • Murad Tukan, Xuan Wu, Samson Zhou, Vladimir Braverman, Dan Feldman

$(j, k)$-projective clustering is the natural generalization of the family of $k$-clustering and $j$-subspace clustering problems.

no code implementations • 7 Mar 2022 • Difan Zou, Jingfeng Wu, Vladimir Braverman, Quanquan Gu, Sham M. Kakade

Stochastic gradient descent (SGD) has achieved great success due to its superior performance in both optimization and generalization.

no code implementations • 18 Dec 2021 • Vishwa S Parekh, Shuhao Lai, Vladimir Braverman, Jeff Leal, Steven Rowe, Jay J Pillai, Michael A Jacobs

Federated learning is increasingly being explored in the field of medical imaging to train deep learning models on large scale datasets distributed across different data centers while preserving privacy by avoiding the need to transfer sensitive patient information.

no code implementations • 12 Oct 2021 • Jingfeng Wu, Difan Zou, Vladimir Braverman, Quanquan Gu, Sham M. Kakade

In this paper, we provide a problem-dependent analysis on the last iterate risk bounds of SGD with decaying stepsize, for (overparameterized) linear regression problems.

1 code implementation • 11 Aug 2021 • Jingfeng Wu, Vladimir Braverman, Lin F. Yang

In particular, for an unknown finite-horizon Markov decision process, the algorithm takes only $\widetilde{\mathcal{O}} (1/\epsilon \cdot (H^3SA / \rho + H^4 S^2 A) )$ episodes of exploration, and is able to obtain an $\epsilon$-optimal policy for a post-revealed reward with sub-optimality gap at least $\rho$, where $S$ is the number of states, $A$ is the number of actions, and $H$ is the length of the horizon, obtaining a nearly \emph{quadratic saving} in terms of $\epsilon$.

no code implementations • NeurIPS 2021 • Difan Zou, Jingfeng Wu, Vladimir Braverman, Quanquan Gu, Dean P. Foster, Sham M. Kakade

Stochastic gradient descent (SGD) exhibits strong algorithmic regularization effects in practice, which has been hypothesized to play an important role in the generalization of modern machine learning approaches.

no code implementations • NeurIPS 2021 • Vladimir Braverman, Avinatan Hassidim, Yossi Matias, Mariano Schain, Sandeep Silwal, Samson Zhou

In this paper, we introduce adversarially robust streaming algorithms for central machine learning and algorithmic tasks, such as regression and clustering, as well as their more general counterparts, subspace embedding, low-rank approximation, and coreset construction.

no code implementations • 17 Apr 2021 • Haoran Li, Aditya Krishnan, Jingfeng Wu, Soheil Kolouri, Praveen K. Pilly, Vladimir Braverman

In practice and due to computational constraints, most SR methods crudely approximate the importance matrix by its diagonal.

no code implementations • 23 Mar 2021 • Difan Zou, Jingfeng Wu, Vladimir Braverman, Quanquan Gu, Sham M. Kakade

More specifically, for SGD with iterate averaging, we demonstrate the sharpness of the established excess risk bound by proving a matching lower bound (up to constant factors).

1 code implementation • NeurIPS 2021 • Jingfeng Wu, Vladimir Braverman, Lin F. Yang

We formalize this problem as an episodic learning problem on a Markov decision process, where transitions are unknown and a reward function is the inner product of a preference vector with pre-specified multi-objective reward functions.

Multi-Objective Reinforcement Learning reinforcement-learning

no code implementations • 11 Nov 2020 • Viska Wei, Nikita Ivkin, Vladimir Braverman, Alexander Szalay

Running machine learning analytics over geographically distributed datasets is a rapidly arising problem in the world of data management policies ensuring privacy and data security.

no code implementations • ICLR 2021 • Jingfeng Wu, Difan Zou, Vladimir Braverman, Quanquan Gu

Understanding the algorithmic bias of \emph{stochastic gradient descent} (SGD) is one of the key challenges in modern machine learning and deep learning theory.

no code implementations • 19 Aug 2020 • Ben Mussay, Daniel Feldman, Samson Zhou, Vladimir Braverman, Margarita Osadchy

Our method is based on the coreset framework and it approximates the output of a layer of neurons/filters by a coreset of neurons/filters in the previous layer and discards the rest.

1 code implementation • ICML 2020 • Jingfeng Wu, Vladimir Braverman, Lin F. Yang

In sum, we obtain adjustable regularization for free for a large class of optimization problems and resolve an open question raised by Neu and Rosasco.

no code implementations • 15 Jul 2020 • Daniel Rothchild, Ashwinee Panda, Enayat Ullah, Nikita Ivkin, Ion Stoica, Vladimir Braverman, Joseph Gonzalez, Raman Arora

A key insight in the design of FetchSGD is that, because the Count Sketch is linear, momentum and error accumulation can both be carried out within the sketch.

2 code implementations • MIDL 2019 • Vishwa S. Parekh, Alex E. Bocchieri, Vladimir Braverman, Michael A. Jacobs

As a result, to develop a radiological decision support system, it would need to be equipped with potentially hundreds of deep learning models with each model trained for a specific task or organ.

no code implementations • 1 Aug 2019 • Alex E. Bocchieri, Vishwa S. Parekh, Kathryn R. Wagner. Shivani Ahlawat, Vladimir Braverman, Doris G. Leung, Michael A. Jacobs

A current clinical challenge is identifying limb girdle muscular dystrophy 2I(LGMD2I)tissue changes in the thighs, in particular, separating fat, fat-infiltrated muscle, and muscle tissue.

no code implementations • ICLR 2020 • Ben Mussay, Margarita Osadchy, Vladimir Braverman, Samson Zhou, Dan Feldman

We propose the first efficient, data-independent neural pruning algorithm with a provable trade-off between its compression rate and the approximation error for any future test sample.

1 code implementation • 29 Jun 2019 • Nikita Ivkin, Edo Liberty, Kevin Lang, Zohar Karnin, Vladimir Braverman

Approximating quantiles and distributions over streaming data has been studied for roughly two decades now.

1 code implementation • ICML 2020 • Jingfeng Wu, Wenqing Hu, Haoyi Xiong, Jun Huan, Vladimir Braverman, Zhanxing Zhu

The gradient noise of SGD is considered to play a central role in the observed strong generalization abilities of deep learning.

2 code implementations • NeurIPS 2019 • Nikita Ivkin, Daniel Rothchild, Enayat Ullah, Vladimir Braverman, Ion Stoica, Raman Arora

Large-scale distributed training of neural networks is often limited by network bandwidth, wherein the communication time overwhelms the local computation time.

1 code implementation • 11 Mar 2019 • Vladimir Braverman, Shaofeng H. -C. Jiang, Robert Krauthgamer, Xuan Wu

We design coresets for Ordered k-Median, a generalization of classical clustering problems such as k-Median and k-Center, that offers a more flexible data analysis, like easily combining multiple objectives (e. g., to increase fairness or for Pareto optimization).

Data Structures and Algorithms

no code implementations • NeurIPS 2018 • Raman Arora, Vladimir Braverman, Jalaj Upadhyay

In this paper, we study the following robust low-rank matrix approximation problem: given a matrix $A \in \R^{n \times d}$, find a rank-$k$ matrix $B$, while satisfying differential privacy, such that $ \norm{ A - B }_p \leq \alpha \mathsf{OPT}_k(A) + \tau,$ where $\norm{ M }_p$ is the entry-wise $\ell_p$-norm and $\mathsf{OPT}_k(A):=\min_{\mathsf{rank}(X) \leq k} \norm{ A - X}_p$.

no code implementations • 22 May 2017 • Lin F. Yang, Vladimir Braverman, Tuo Zhao, Mengdi Wang

We formulate this into a nonconvex stochastic factorization problem and propose an efficient and scalable stochastic generalized Hebbian algorithm.

Cannot find the paper you are looking for? You can
Submit a new open access paper.

Contact us on:
hello@paperswithcode.com
.
Papers With Code is a free resource with all data licensed under CC-BY-SA.