33 citations · 54 across the 34 of their papers we have counts for
20 papers · 1 filter
Sequential Linearithmic Time Optimal Unimodal Fitting When Minimizing Univariate Linear Losses
Kaan Gokcesu, Hakan Gokcesu
This paper focuses on optimal unimodal transformation of the score outputs of a univariate learning model under linear loss functions. We demonstrate that the optimal mapping betwe…
A Note On Nonlinear Regression Under L2 Loss
Kaan Gokcesu, Hakan Gokcesu
We investigate the nonlinear regression problem under L2 loss (square loss) functions. Traditional nonlinear regression models often result in non-convex optimization problems with…
Efficient Lipschitzian Global Optimization of Hölder Continuous Multivariate Functions
Kaan Gokcesu, Hakan Gokcesu
This study presents an effective global optimization technique designed for multivariate functions that are Hölder continuous. Unlike traditional methods that construct lower bound…
Formulation of Weighted Average Smoothing as a Projection of the Origin onto a Convex Polytope
Kaan Gokcesu, Hakan Gokcesu
Our study focuses on determining the best weight windows for a weighted moving average smoother under squared loss. We show that there exists an optimal weight window that is symme…
Data Dependent Regret Guarantees Against General Comparators for Full or Bandit Feedback
Kaan Gokcesu, Hakan Gokcesu
We study the adversarial online learning problem and create a completely online algorithmic framework that has data dependent regret guarantees in both full expert feedback and ban…
An Auto-Regressive Formulation for Smoothing and Moving Mean with Exponentially Tapered Windows
Kaan Gokcesu, Hakan Gokcesu
We investigate an auto-regressive formulation for the problem of smoothing time-series by manipulating the inherent objective function of the traditional moving mean smoothers. Not…
Efficient Minimax Optimal Global Optimization of Lipschitz Continuous Multivariate Functions
Kaan Gokcesu, Hakan Gokcesu
In this work, we propose an efficient minimax optimal global optimization algorithm for multivariate Lipschitz continuous functions. To evaluate the performance of our approach, we…
A Log-Linear Time Sequential Optimal Calibration Algorithm for Quantized Isotonic L2 Regression
Kaan Gokcesu, Hakan Gokcesu
We study the sequential calibration of estimations in a quantized isotonic L2 regression setting. We start by showing that the optimal calibrated quantized estimations can be acqui…
Second Order Regret Bounds Against Generalized Expert Sequences under Partial Bandit Feedback
Kaan Gokcesu, Hakan Gokcesu
We study the problem of expert advice under partial bandit feedback setting and create a sequential minimax optimal algorithm. Our algorithm works with a more general partial monit…
Low Regret Binary Sampling Method for Efficient Global Optimization of Univariate Functions
Kaan Gokcesu, Hakan Gokcesu
In this work, we propose a computationally efficient algorithm for the problem of global optimization in univariate loss functions. For the performance evaluation, we study the cum…
Efficient, Anytime Algorithms for Calibration with Isotonic Regression under Strictly Convex Losses
Kaan Gokcesu, Hakan Gokcesu
We investigate the calibration of estimations to increase performance with an optimal monotone transform on the estimator outputs. We start by studying the traditional square error…
Near-Linear Time Algorithm with Near-Logarithmic Regret Per Switch for Mixable/Exp-Concave Losses
Kaan Gokcesu, Hakan Gokcesu
We investigate the problem of online learning, which has gained significant attention in recent years due to its applicability in a wide range of fields from machine learning to ga…
Generalized Translation and Scale Invariant Online Algorithm for Adversarial Multi-Armed Bandits
Kaan Gokcesu, Hakan Gokcesu
We study the adversarial multi-armed bandit problem and create a completely online algorithmic framework that is invariant under arbitrary translations and scales of the arm losses…
Nonparametric Extrema Analysis in Time Series for Envelope Extraction, Peak Detection and Clustering
Kaan Gokcesu, Hakan Gokcesu
In this paper, we propose a nonparametric approach that can be used in envelope extraction, peak-burst detection and clustering in time series. Our problem formalization results in…
Optimally Efficient Sequential Calibration of Binary Classifiers to Minimize Classification Error
Kaan Gokcesu, Hakan Gokcesu
In this work, we aim to calibrate the score outputs of an estimator for the binary classification problem by finding an 'optimal' mapping to class probabilities, where the 'optimal…
Optimal and Efficient Algorithms for General Mixable Losses against Switching Oracles
Kaan Gokcesu, Hakan Gokcesu
We investigate the problem of online learning, which has gained significant attention in recent years due to its applicability in a wide range of fields from machine learning to ga…
Cumulative Regret Analysis of the Piyavskii--Shubert Algorithm and Its Variants for Global Optimization
Kaan Gokcesu, Hakan Gokcesu
We study the problem of global optimization, where we analyze the performance of the Piyavskii--Shubert algorithm and its variants. For any given time duration , instead of the…
A Generalized Online Algorithm for Translation and Scale Invariant Prediction with Expert Advice
Kaan Gokcesu, Hakan Gokcesu
In this work, we aim to create a completely online algorithmic framework for prediction with expert advice that is translation-free and scale-free of the expert losses. Our goal is…
Minimax Optimal Algorithms for Adversarial Bandit Problem with Multiple Plays
N. Mert Vural, Hakan Gokcesu, Kaan Gokcesu +1
We investigate the adversarial bandit problem with multiple plays under semi-bandit feedback. We introduce a highly efficient algorithm that asymptotically achieves the performance…
Sequential Outlier Detection based on Incremental Decision Trees
Mohammadreza Mohaghegh Neyshabouri, Suleyman Serdar Kozat
We introduce an online outlier detection algorithm to detect outliers in a sequentially observed data stream. For this purpose, we use a two-stage filtering and hedging approach. I…