Zobrazeno 1 - 10
of 651
pro vyhledávání: '"WEISSMAN, TSACHY"'
Autor:
Sagan, Naomi, Weissman, Tsachy
We propose and study a family of universal sequential probability assignments on individual sequences, based on the incremental parsing procedure of the Lempel-Ziv (LZ78) compression algorithm. We show that the normalized log loss under any of these
Externí odkaz:
http://arxiv.org/abs/2410.06589
Autor:
Panda, Ashwinee, Isik, Berivan, Qi, Xiangyu, Koyejo, Sanmi, Weissman, Tsachy, Mittal, Prateek
Existing methods for adapting large language models (LLMs) to new tasks are not suited to multi-task adaptation because they modify all the model weights -- causing destructive interference between tasks. The resulting effects, such as catastrophic f
Externí odkaz:
http://arxiv.org/abs/2406.16797
Simulating quantum circuits on classical hardware is a powerful and necessary tool for developing and testing quantum algorithms and hardware as well as evaluating claims of quantum supremacy in the Noisy Intermediate-Scale Quantum (NISQ) regime. Sch
Externí odkaz:
http://arxiv.org/abs/2401.11088
Autor:
Isik, Berivan, Pase, Francesco, Gunduz, Deniz, Koyejo, Sanmi, Weissman, Tsachy, Zorzi, Michele
The high communication cost of sending model updates from the clients to the server is a significant bottleneck for scalable federated learning (FL). Among existing approaches, state-of-the-art bitrate-accuracy tradeoffs have been achieved using stoc
Externí odkaz:
http://arxiv.org/abs/2306.12625
We study the mean estimation problem under communication and local differential privacy constraints. While previous work has proposed \emph{order}-optimal algorithms for the same problem (i.e., asymptotically optimal as we spend more bits), \emph{exa
Externí odkaz:
http://arxiv.org/abs/2306.04924
Autor:
Weissman, Tsachy
Inspired by recent work on compression with and for young humans, the success of transform-based approaches to information processing, and the rise of powerful language-based AI, we propose \emph{textual transform coding}. It shares some of its key p
Externí odkaz:
http://arxiv.org/abs/2305.01857
Autor:
Pergament, Evgenya, Tandon, Pulkit, Rippel, Oren, Bourdev, Lubomir, Anderson, Alexander G., Olshausen, Bruno, Weissman, Tsachy, Katti, Sachin, Tatwawadi, Kedar
Human perception is at the core of lossy video compression, with numerous approaches developed for perceptual quality assessment and improvement over the past two decades. In the determination of perceptual quality, different spatio-temporal regions
Externí odkaz:
http://arxiv.org/abs/2212.10674
With the advent and increasing consolidation of e-commerce, digital advertising has very recently replaced traditional advertising as the main marketing force in the economy. In the past four years, a particularly important development in the digital
Externí odkaz:
http://arxiv.org/abs/2211.06358
We consider the maximum coding rate achievable by uniformly-random codes for the deletion channel. We prove an upper bound that's within 0.1 of the best known lower bounds for all values of the deletion probability $d,$ and much closer for small and
Externí odkaz:
http://arxiv.org/abs/2210.07437
One main challenge in federated learning is the large communication cost of exchanging weight updates from clients to the server at each round. While prior work has made great progress in compressing the weight updates through gradient compression me
Externí odkaz:
http://arxiv.org/abs/2209.15328