Alon Orlitsky
where else to find them
no profile links on file
what they talk about
where they keep going back
no series more than once — all 2 in the filters
on a stage with
never shared a talk
who talks about the same things
nobody close enough yet
| title | conference | date |
|---|---|---|
| Interactive and Amortized Communication – An Information Theoretic Perspective | Information Theory in Complexity Theory and Combinatorics 2015 | 2015-04-24 |
Examines concrete gaps: the indexing (league) example shows one-way needs ~log n bits while a two-message protocol sends one index plus a single bit so… | ||
| Distribution Estimation and Applications I | Information Theory Boot Camp 2015 | 2015-01-13 |
Establishes concrete minimax rates and practical reductions: empirical frequencies give L1 risk Θ(√(K/N)) and KL risk ≈ (K−1)/(2N), so naive IID learning needs… | ||
| Distribution Estimation and Applications II | Information Theory Boot Camp 2015 | 2015-01-13 |
Estimators for combined probabilities (s0, s1, …) use Poissonization and show Good–Turing is unbiased: its expected g_mu equals E[s_mu], fixing empirical… | ||
| Distribution Estimation and Applications III | Information Theory Boot Camp 2015 | 2015-01-13 |
Establishes concrete limits and algorithms: empirical frequency yields L1 error roughly sqrt(k/n) so sample complexity grows quadratically in k; worst-case… | ||
| nothing matches | ||