activity
20062026
most citedClassification vs regression in overparameterized regimes: Does the loss function matter?

45 citations · 293 across the 45 of their papers we have counts for

collaborators
Showing 2006Show all

7 papers · 1 filter

cs.IT2006★ 7 cited

Anytime coding on the infinite bandwidth AWGN channel: A sequential semi-orthogonal optimal code

Anant Sahai

It is well known that orthogonal coding can be used to approach the Shannon capacity of the power-constrained AWGN channel without a bandwidth constraint. This correspondence descr…

cs.IT2006★ 3 cited

How to beat the sphere-packing bound with feedback

Anant Sahai

The sphere-packing bound bounds the reliability function for fixed-length block-codes. For symmetric channels, it remains a valid bound even when strictly causal noisel…

cs.IT2006★ 3 cited

Lossless coding for distributed streaming sources

Cheng Chang, Stark Draper, Anant Sahai

Distributed source coding is traditionally viewed in the block coding context -- all the source symbols are known in advance at the encoders. This paper instead considers a streami…

cs.IT2006★ 5 cited

The necessity and sufficiency of anytime capacity for stabilization of a linear system over a noisy communication link, Part II: vector systems

Anant Sahai, Sanjoy Mitter

In part I, we reviewed how Shannon's classical notion of capacity is not sufficient to characterize a noisy communication channel if the channel is intended to be used as part of a…

cs.IT2006★ 18 cited

Source coding and channel requirements for unstable processes

Anant Sahai, Sanjoy Mitter

Our understanding of information in systems has been based on the foundation of memoryless processes. Extensions to stable Markov and auto-regressive processes are classical. Berge…

cs.IT2006★ 3 cited

Why block length and delay behave differently if feedback is present

Anant Sahai

For output-symmetric DMCs at even moderately high rates, fixed-block-length communication systems show no improvements in their error exponents with feedback. In this paper, we stu…