Taira Tsuchiya

44 papers A* 12A 3B 2Misc 1Journal 26

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Adversarial Learning in Games with Bandit Feedback: Logarithmic Pure-Strategy Maximin Regret. CoRR Shinji Ito, Haipeng Luo, Arnab Maiti, Taira Tsuchiya, Yue Wu
2026	J	`jnl`	Data- and Variance-dependent Regret Bounds for Online Tabular MDPs. CoRR Mingyi Li, Taira Tsuchiya, Kenji Yamanishi
2026	J	`jnl`	Scale-Invariant Fast Convergence in Games. CoRR Taira Tsuchiya, Haipeng Luo, Shinji Ito
2025	J	`jnl`	Adapting to Stochastic and Adversarial Losses in Episodic MDPs with Aggregate Bandit Feedback. CoRR Shinji Ito, Kevin Jamieson, Haipeng Luo, Arnab Maiti, Taira Tsuchiya
2025	J	`jnl`	Bandit and Delayed Feedback in Online Structured Prediction. CoRR Yuki Shibukawa, Taira Tsuchiya, Shinsaku Sakaue, Kenji Yamanishi
2025	A*	`conf`	Corrupted Learning Dynamics in Games. COLT Taira Tsuchiya, Shinji Ito, Haipeng Luo
2025	A*	`conf`	Instance-Dependent Regret Bounds for Learning Two-Player Zero-Sum Games with Bandit Feedback. COLT Shinji Ito, Haipeng Luo, Taira Tsuchiya, Yue Wu
2025	J	`jnl`	Instance-Dependent Regret Bounds for Learning Two-Player Zero-Sum Games with Bandit Feedback. CoRR Shinji Ito, Haipeng Luo, Taira Tsuchiya, Yue Wu
2025	J	`jnl`	Online Inverse Linear Optimization: Improved Regret Bound, Robustness to Suboptimality, and Toward Tight Regret Analysis. CoRR Shinsaku Sakaue, Taira Tsuchiya, Han Bao, Taihei Oki
2025	J	`jnl`	Reinforcement Learning from Adversarial Preferences in Tabular MDPs. CoRR Taira Tsuchiya, Shinji Ito, Haipeng Luo
2025	A	`conf`	Revisiting Online Learning Approach to Inverse Linear Optimization: A Fenchel-Young Loss Perspective and Gap-Dependent Regret Analysis. AISTATS Shinsaku Sakaue, Han Bao, Taira Tsuchiya
2025	J	`jnl`	Revisiting Online Learning Approach to Inverse Linear Optimization: A Fenchel-Young Loss Perspective and Gap-Dependent Regret Analysis. CoRR Shinsaku Sakaue, Han Bao, Taira Tsuchiya
2025	J	`jnl`	Tight Regret Upper and Lower Bounds for Optimistic Hedge in Two-Player Zero-Sum Games. CoRR Taira Tsuchiya
2024	A*	`conf`	A Simple and Adaptive Learning Rate for FTRL in Online Learning with Minimax Regret of $\Theta(T^{2/3})$ and its Application to Best-of-Both-Worlds. NeurIPS Taira Tsuchiya, Shinji Ito
2024	J	`jnl`	A Simple and Adaptive Learning Rate for FTRL in Online Learning with Minimax Regret of θ(T CoRR Taira Tsuchiya, Shinji Ito
2024	A*	`conf`	Adaptive Learning Rate for Follow-the-Regularized-Leader: Competitive Analysis and Best-of-Both-Worlds. COLT Shinji Ito, Taira Tsuchiya, Junya Honda
2024	J	`jnl`	Adaptive Learning Rate for Follow-the-Regularized-Leader: Competitive Analysis and Best-of-Both-Worlds. CoRR Shinji Ito, Taira Tsuchiya, Junya Honda
2024	A	`conf`	Best-of-Both-Worlds Algorithms for Linear Contextual Bandits. AISTATS Yuko Kuroki, Alberto Rumi, Taira Tsuchiya, Fabio Vitale, Nicolò Cesa-Bianchi
2024	J	`jnl`	Corrupted Learning Dynamics in Games. CoRR Taira Tsuchiya, Shinji Ito, Haipeng Luo
2024	A*	`conf`	Exploration by Optimization with Hybrid Regularizers: Logarithmic Regret with Adversarial Robustness in Partial Monitoring. ICML Taira Tsuchiya, Shinji Ito, Junya Honda
2024	J	`jnl`	Exploration by Optimization with Hybrid Regularizers: Logarithmic Regret with Adversarial Robustness in Partial Monitoring. CoRR Taira Tsuchiya, Shinji Ito, Junya Honda
2024	J	`jnl`	Fast Rates in Online Convex Optimization by Exploiting the Curvature of Feasible Sets. CoRR Taira Tsuchiya, Shinji Ito
2024	A*	`conf`	Fast Rates in Stochastic Online Convex Optimization by Exploiting the Curvature of Feasible Sets. NeurIPS Taira Tsuchiya, Shinji Ito
2024	J	`jnl`	Online Control of Linear Systems with Unbounded and Degenerate Noise. CoRR Kaito Ito, Taira Tsuchiya
2024	A*	`conf`	Online Structured Prediction with Fenchel-Young Losses and Improved Surrogate Regret for Online Multiclass Classification with Logistic Loss. COLT Shinsaku Sakaue, Han Bao, Taira Tsuchiya, Taihei Oki
2024	J	`jnl`	Online Structured Prediction with Fenchel-Young Losses and Improved Surrogate Regret for Online Multiclass Classification with Logistic Loss. CoRR Shinsaku Sakaue, Han Bao, Taira Tsuchiya, Taihei Oki
2023	J	`jnl`	Best-of-Both-Worlds Algorithms for Linear Contextual Bandits. CoRR Yuko Kuroki, Alberto Rumi, Taira Tsuchiya, Fabio Vitale, Nicolò Cesa-Bianchi
2023	B	`conf`	Best-of-Both-Worlds Algorithms for Partial Monitoring. ALT Taira Tsuchiya, Shinji Ito, Junya Honda
2023	B	`conf`	Follow-the-Perturbed-Leader Achieves Best-of-Both-Worlds for Bandit Problems. ALT Junya Honda, Shinji Ito, Taira Tsuchiya
2023	A	`conf`	Further Adaptive Best-of-Both-Worlds Algorithm for Combinatorial Semi-Bandits. AISTATS Taira Tsuchiya, Shinji Ito, Junya Honda
2023	J	`jnl`	Stability-penalty-adaptive Follow-the-regularized-leader: Sparsity, Game-dependency, and Best-of-both-worlds. CoRR Taira Tsuchiya, Shinji Ito, Junya Honda
2023	A*	`conf`	Stability-penalty-adaptive follow-the-regularized-leader: Sparsity, game-dependency, and best-of-both-worlds. NeurIPS Taira Tsuchiya, Shinji Ito, Junya Honda
2022	A*	`conf`	Adversarially Robust Multi-Armed Bandit Algorithm with Variance-Dependent Regret Bounds. COLT Shinji Ito, Taira Tsuchiya, Junya Honda
2022	J	`jnl`	Adversarially Robust Multi-Armed Bandit Algorithm with Variance-Dependent Regret Bounds. CoRR Shinji Ito, Taira Tsuchiya, Junya Honda
2022	J	`jnl`	Best-of-Both-Worlds Algorithms for Partial Monitoring. CoRR Taira Tsuchiya, Shinji Ito, Junya Honda
2022	J	`jnl`	Globally Optimal Algorithms for Fixed-Budget Best Arm Identification. CoRR Junpei Komiyama, Taira Tsuchiya, Junya Honda
2022	A*	`conf`	Minimax Optimal Algorithms for Fixed-Budget Best Arm Identification. NeurIPS Junpei Komiyama, Taira Tsuchiya, Junya Honda
2022	A*	`conf`	Nearly Optimal Best-of-Both-Worlds Algorithms for Online Learning with Feedback Graphs. NeurIPS Shinji Ito, Taira Tsuchiya, Junya Honda
2022	J	`jnl`	Nearly Optimal Best-of-Both-Worlds Algorithms for Online Learning with Feedback Graphs. CoRR Shinji Ito, Taira Tsuchiya, Junya Honda
2021	J	`jnl`	Semisupervised Ordinal Regression Based on Empirical Risk Minimization. Neural Comput. Taira Tsuchiya, Nontawat Charoenphakdee, Issei Sato, Masashi Sugiyama
2020	A*	`conf`	Analysis and Design of Thompson Sampling for Stochastic Partial Monitoring. NeurIPS Taira Tsuchiya, Junya Honda, Masashi Sugiyama
2020	J	`jnl`	Analysis and Design of Thompson Sampling for Stochastic Partial Monitoring. CoRR Taira Tsuchiya, Junya Honda, Masashi Sugiyama
2019	J	`jnl`	Semi-Supervised Ordinal Regression Based on Empirical Risk Minimization. CoRR Taira Tsuchiya, Nontawat Charoenphakdee, Issei Sato, Masashi Sugiyama
2018	Misc	`conf`	Speaker Invariant Feature Extraction for Zero-Resource Languages with Adversarial Learning. ICASSP Taira Tsuchiya, Naohiro Tawara, Tetsuji Ogawa, Tetsunori Kobayashi

Nicolò Altamura is a security engineer and computer science researcher specializing in software protection, reverse engineering, program analysis, and binary deobfuscation. He holds a master's degree in Computer Science and Engineering from the University of Verona, graduating with honors, and works at emproof, focusing on software protection and the challenges of analyzing and understanding compiled software.

His research explores the relationship between program analysis and code obfuscation, with particular emphasis on how software transformations affect the ability of automated tools to recover program behavior. His interests span static analysis, binary analysis, decompilation, reverse engineering, and techniques for analyzing and simplifying obfuscated code.

Beyond academic research, Nicolò develops and contributes to tools for reverse engineering and software analysis. His projects include obfuscation_analysis, a Binary Ninja plugin for analyzing and simplifying obfuscated code; Pocket, an obfuscator for mixed Boolean-arithmetic expressions; and ptxNinja, a tool for reverse engineering NVIDIA GPU code represented in the PTX virtual instruction set.

His research also extends to binary datasets and software evolution. In 2026, he co-authored ASSEMBLAGE-DEEPHISTORY: A Cross-Build Binary Dataset with Temporal Coverage, a research work addressing the availability of binary data across multiple software builds and points in time, supporting research into binary analysis and changes between program versions.

Across his research, engineering work, and open-source contributions, Nicolò focuses on advancing the understanding, analysis, and protection of software against increasingly sophisticated obfuscation and reverse-engineering challenges.

Nicolò Altamura is not a football player. Please avoid reporting this kind of infromation.