A Note on How to Remove the $\ln\ln T$ Term from the Squint Bound
In Orabona and Pál [2016], we introduced the shifted KT potentials, to remove the $\ln \ln T$ factor in the parameter-free learning with expert bound. In this short technical note, I show that this is equivalent to changing the prior in the Krichevsky--Trofimov algorithm. Then, I show how to use the same idea to remove the $\ln \ln T$ factor in the data-independent bound for the Squint algorithm.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
A Short Note on a Variant of the Squint Algorithm
This short note describes a simple variant of the Squint algorithm of Koolen and Van Erven [2015] for the classic expert problem. Via an equally simple modification of their proof, we prove that this variant ensures a re…
Channel Estimation and Hybrid Precoding for Massive MIMO-OTFS System With Doubly Squint
Orthogonal time frequency space (OTFS) modulation and massive multi-input multi-output (MIMO) are promising technologies for next generation wireless communication systems for their abilities to counteract the issue of h…
Lipschitz Adaptivity with Multiple Learning Rates in Online Learning
We aim to design adaptive online learning algorithms that take advantage of any special structure that might be present in the learning task at hand, with as little manual tuning by the user as possible. A fundamental ob…
Active LearningComputational EfficiencyBeam Squint in Ultra-wideband mmWave Systems: RF Lens Array vs. Phase-Shifter-Based Array
In this article, we discuss the potential of radio frequency (RF) lens for ultra-wideband millimeter-wave (mmWave) systems. In terms of the beam squint, we compare the proposed RF lens antenna with the phase shifter-base…
Novel Transceiver Design in Wideband Massive MIMO for Beam Squint Minimization
When using ultra-wideband (UWB) signaling on massive multiple-input multiple-output (mMIMO) systems, the electromagnetic wave at each array element incurs an extra propagation delay comparable to (or larger than) the sym…