Search Results for author:
Found 5 papers, 0 papers with code
k*-Nearest Neighbors: From Global to Local
The weighted k-nearest neighbors algorithm is one of the most fundamental non-parametric methods in pattern recognition and machine learning.
Multi-armed Bandits: Competing with Optimal Sequences
Our main result is a regret guarantee that scales with the variation parameter of the environment, without requiring any prior knowledge about it whatsoever.
Online Learning for Adversaries with Memory: Price of Past Mistakes
In this work we extend the notion of learning with memory to the general Online Convex Optimization (OCO) framework, and present two algorithms that attain low regret.
Budget-Constrained Item Cold-Start Handling in Collaborative Filtering Recommenders via Optimal Design
It is well known that collaborative filtering (CF) based recommender systems provide better modeling of users and items associated with considerable rating history.
Online Convex Optimization Against Adversaries with Memory and Application to Statistical Arbitrage
The framework of online learning with memory naturally captures learning problems with temporal constraints, and was previously studied for the experts setting.
