all AI news
Tricking the Hashing Trick: A Tight Lower Bound on the Robustness of CountSketch to Adaptive Inputs. (arXiv:2207.00956v1 [cs.DS])
July 5, 2022, 1:10 a.m. | Edith Cohen, Jelani Nelson, Tamás Sarlós, Uri Stemmer
cs.LG updates on arXiv.org arxiv.org
CountSketch and Feature Hashing (the "hashing trick") are popular randomized
dimensionality reduction methods that support recovery of $\ell_2$-heavy
hitters (keys $i$ where $v_i^2 > \epsilon \|\boldsymbol{v}\|_2^2$) and
approximate inner products. When the inputs are {\em not adaptive} (do not
depend on prior outputs), classic estimators applied to a sketch of size
$O(\ell/\epsilon)$ are accurate for a number of queries that is exponential in
$\ell$. When inputs are adaptive, however, an adversarial input can be
constructed after $O(\ell)$ queries with the …
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne
Senior Machine Learning Engineer (MLOps)
@ Promaton | Remote, Europe
Business Intelligence Analyst
@ Rappi | COL-Bogotá
Applied Scientist II
@ Microsoft | Redmond, Washington, United States