Zobrazeno 1 - 10
of 25
pro vyhledávání: '"Ivkin, Nikita"'
Autor:
Das, Piali, Perrone, Valerio, Ivkin, Nikita, Bansal, Tanya, Karnin, Zohar, Shen, Huibin, Shcherbatyi, Iaroslav, Elor, Yotam, Wu, Wilton, Zolic, Aida, Lienart, Thibaut, Tang, Alex, Ahmed, Amr, Faddoul, Jean Baptiste, Jenatton, Rodolphe, Winkelmolen, Fela, Gautier, Philip, Dirac, Leo, Perunicic, Andre, Miladinovic, Miroslav, Zappella, Giovanni, Archambeau, Cédric, Seeger, Matthias, Dutt, Bhaskar, Rouesnel, Laurence
AutoML systems provide a black-box solution to machine learning problems by selecting the right way of processing features, choosing an algorithm and tuning the hyperparameters of the entire pipeline. Although these systems perform well on many datas
Externí odkaz:
http://arxiv.org/abs/2012.08483
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. Visualizing high dimensional data using tools such as t-distributed
Externí odkaz:
http://arxiv.org/abs/2011.06103
Zero-shot hyperparameter optimization (HPO) is a simple yet effective use of transfer learning for constructing a small list of hyperparameter (HP) configurations that complement each other. That is to say, for any given dataset, at least one of them
Externí odkaz:
http://arxiv.org/abs/2007.13382
Autor:
Rothchild, Daniel, Panda, Ashwinee, Ullah, Enayat, Ivkin, Nikita, Stoica, Ion, Braverman, Vladimir, Gonzalez, Joseph, Arora, Raman
Existing approaches to federated learning suffer from a communication bottleneck as well as convergence issues due to sparse client participation. In this paper we introduce a novel algorithm, called FetchSGD, to overcome these challenges. FetchSGD c
Externí odkaz:
http://arxiv.org/abs/2007.07682
Cosmological N-body simulations are crucial for understanding how the Universe evolves. Studying large-scale distributions of matter in these simulations and comparing them to observations usually involves detecting dense clusters of particles called
Externí odkaz:
http://arxiv.org/abs/1912.11432
Approximating quantiles and distributions over streaming data has been studied for roughly two decades now. Recently, Karnin, Lang, and Liberty proposed the first asymptotically optimal algorithm for doing so. This manuscript complements their theore
Externí odkaz:
http://arxiv.org/abs/1907.00236
Autor:
Ivkin, Nikita, Rothchild, Daniel, Ullah, Enayat, Braverman, Vladimir, Stoica, Ion, Arora, Raman
Large-scale distributed training of neural networks is often limited by network bandwidth, wherein the communication time overwhelms the local computation time. Motivated by the success of sketching methods in sub-linear/streaming algorithms, we intr
Externí odkaz:
http://arxiv.org/abs/1903.04488
Extracting information from electronic health records (EHR) is a challenging task since it requires prior knowledge of the reports and some natural language processing algorithm (NLP). With the growing number of EHR implementations, such knowledge is
Externí odkaz:
http://arxiv.org/abs/1809.02665
Autor:
Ivkin, Nikita, Liu, Zaoxing, Yang, Lin F., Kumar, Srinivas Suresh, Lemson, Gerard, Neyrinck, Mark, Szalay, Alexander S., Braverman, Vladimir, Budavari, Tamas
Cosmological $N$-body simulations play a vital role in studying models for the evolution of the Universe. To compare to observations and make a scientific inference, statistic analysis on large simulation datasets, e.g., finding halos, obtaining mult
Externí odkaz:
http://arxiv.org/abs/1711.00975
Autor:
Braverman, Vladimir, Chestnut, Stephen R., Ivkin, Nikita, Nelson, Jelani, Wang, Zhengyu, Woodruff, David P.
The task of finding heavy hitters is one of the best known and well studied problems in the area of data streams. One is given a list $i_1,i_2,\ldots,i_m\in[n]$ and the goal is to identify the items among $[n]$ that appear frequently in the list. In
Externí odkaz:
http://arxiv.org/abs/1603.00759