Zobrazeno 1 - 10
of 569
pro vyhledávání: '"Sarlós P"'
Cardinality sketches are compact data structures for representing sets or vectors, enabling efficient approximation of their cardinality (or the number of nonzero entries). These sketches are space-efficient, typically requiring only logarithmic stor
Externí odkaz:
http://arxiv.org/abs/2411.06370
Autor:
Choromanski, Krzysztof, Sehanobish, Arijit, Chowdhury, Somnath Basu Roy, Lin, Han, Dubey, Avinava, Sarlos, Tamas, Chaturvedi, Snigdha
We present a new class of fast polylog-linear algorithms based on the theory of structured matrices (in particular low displacement rank) for integrating tensor fields defined on weighted trees. Several applications of the resulting fast tree-field i
Externí odkaz:
http://arxiv.org/abs/2406.15881
Autor:
Brigitta Teutsch, Eszter Boros, Szilárd Váncsa, Alex Váradi, Levente Frim, Szabolcs Kiss, Fanni Dembrovszky, Zsuzsanna Helyes, Sarlós Patrícia, Hegyi Péter, Bálint Erőss
Publikováno v:
Therapeutic Advances in Gastroenterology, Vol 14 (2021)
Background: Small bowel enteropathy (SBE) is a complication of nonsteroidal anti-inflammatory drug (NSAID) therapy occurring in 71% of NSAID users. We aimed to analyse the efficacy and safety of medications to prevent and treat NSAID-induced SBE in r
Externí odkaz:
https://doaj.org/article/ed05d3403332428980b92f8ac47313e6
One of the most basic problems for studying the "price of privacy over time" is the so called private counter problem, introduced by Dwork et al. (2010) and Chan et al. (2010). In this problem, we aim to track the number of events that occur over tim
Externí odkaz:
http://arxiv.org/abs/2403.00028
The Private Aggregation of Teacher Ensembles (PATE) framework is a versatile approach to privacy-preserving machine learning. In PATE, teacher models that are not privacy-preserving are trained on distinct portions of sensitive data. Privacy-preservi
Externí odkaz:
http://arxiv.org/abs/2312.02132
Autor:
Leal, Isabel, Choromanski, Krzysztof, Jain, Deepali, Dubey, Avinava, Varley, Jake, Ryoo, Michael, Lu, Yao, Liu, Frederick, Sindhwani, Vikas, Vuong, Quan, Sarlos, Tamas, Oslund, Ken, Hausman, Karol, Rao, Kanishka
We present Self-Adaptive Robust Attention for Robotics Transformers (SARA-RT): a new paradigm for addressing the emerging challenge of scaling up Robotics Transformers (RT) for on-robot deployment. SARA-RT relies on the new method of fine-tuning prop
Externí odkaz:
http://arxiv.org/abs/2312.01990
Inspired by fast algorithms in natural language processing, we study low rank approximation in the entrywise transformed setting where we want to find a good rank $k$ approximation to $f(U \cdot V)$, where $U, V^\top \in \mathbb{R}^{n \times r}$ are
Externí odkaz:
http://arxiv.org/abs/2311.01960
Autor:
Choromanski, Krzysztof Marcin, Li, Shanda, Likhosherstov, Valerii, Dubey, Kumar Avinava, Luo, Shengjie, He, Di, Yang, Yiming, Sarlos, Tamas, Weingarten, Thomas, Weller, Adrian
We propose a new class of linear Transformers called FourierLearner-Transformers (FLTs), which incorporate a wide range of relative positional encoding mechanisms (RPEs). These include regular RPE techniques applied for sequential data, as well as no
Externí odkaz:
http://arxiv.org/abs/2302.01925
Autor:
Choromanski, Krzysztof, Sehanobish, Arijit, Lin, Han, Zhao, Yunfan, Berger, Eli, Parshakova, Tetiana, Pan, Alvin, Watkins, David, Zhang, Tianyi, Likhosherstov, Valerii, Chowdhury, Somnath Basu Roy, Dubey, Avinava, Jain, Deepali, Sarlos, Tamas, Chaturvedi, Snigdha, Weller, Adrian
Publikováno v:
ICML 2023
We present two new classes of algorithms for efficient field integration on graphs encoding point clouds. The first class, SeparatorFactorization(SF), leverages the bounded genus of point cloud mesh graphs, while the second class, RFDiffusion(RFD), u
Externí odkaz:
http://arxiv.org/abs/2302.00942
Autor:
Likhosherstov, Valerii, Choromanski, Krzysztof, Dubey, Avinava, Liu, Frederick, Sarlos, Tamas, Weller, Adrian
The problem of efficient approximation of a linear operator induced by the Gaussian or softmax kernel is often addressed using random features (RFs) which yield an unbiased approximation of the operator's result. Such operators emerge in important ap
Externí odkaz:
http://arxiv.org/abs/2302.00787