Journal of the ACM
PulseAugur coverage of Journal of the ACM — every cluster mentioning Journal of the ACM across labs, papers, and developer communities, ranked by signal.
3 day(s) with sentiment data
-
New algorithm achieves nearly linear private learning for Littlestone classes
Researchers have developed a new algorithm for differentially private learning, significantly improving the sample complexity for learning Littlestone classes. The new bound is nearly linear, $O(d\log d)$, a substantial…
-
New algorithm computes normal-form correlated equilibria in Markov games
Researchers have developed the first efficient algorithm for computing normal-form correlated equilibria (NFCEs) in finite-horizon Markov games. The algorithm runs in time $S(AH/\epsilon)^{O(n)}$ for $n$ players, $S$ st…
-
New research clarifies optimal scales for machine learning learnability
A new research paper titled "Scale-Sensitive Shattering: Learnability and Evaluability at Optimal Scale" delves into the optimal scales for real-valued function classes to exhibit uniform convergence and learnability. T…
-
New research improves randomized metric distortion bound to 2.3282
Researchers have improved the upper bound for randomized metric distortion in metric social choice to 2.3282. This new bound, achieved by mixing a random-size stable lottery with Integrated Veto, surpasses the previous …
-
New perturbation method reduces matrix condition number with less data
Researchers have developed a new method for perturbing matrices that significantly reduces computational costs compared to existing techniques. This new approach requires generating and storing only O(n) random numbers,…