33 citations · 42 across the 16 of their papers we have counts for
21 papers
Information-Theoretic Generalization for Set-Input Optimization-Valued Objectives
Futoshi Futami, Masahiro Fujisawa
Modern machine learning is increasingly evaluated using criteria such as multicalibration, CVaR, and Cressie-Read DRO, which target subgroup reliability, tail risk, and distributio…
Nambu's Dynamics, Strings and Gravitized Quantum Theory
Tristan Hübsch, Djordje Minic
In this article we present a new view on string theory that is rooted in quantum foundations extended to the domain of quantum gravity in the form of gravitized quantum theory, in…
ProbabilityBench: Model Evaluation and Calibration with Exact Ground-Truth Uncertainty
Yuyang Dai, Yuting Tang, Futoshi Futami +1
Evaluating model uncertainty on real-world data is challenging because each instance provides only a single observed label, leaving true conditional class probabilities unknown. To…
Hierarchical Utility Calibration for Structured Multiclass Decisions
Futoshi Futami, Jerry Huang, Ichiro Takeuchi
In multiclass probabilistic prediction, Utility Calibration (UC), which focuses auditing on specified utilities, has recently received attention as a way to guarantee downstream de…
Information-Theoretic Generalization Bounds for Sequential Decision Making
Futoshi Futami, Masahiro Fujisawa
Information-theoretic generalization bounds based on the supersample construction are a central tool for algorithm-dependent generalization analysis in the batch i.i.d. setting. Ho…
Unified Approach for Weakly Supervised Multicalibration
Futoshi Futami, Takashi Ishida
Multicalibration requires predicted scores to agree with label probabilities across rich families of subgroups and score-dependent tests, but existing methods require clean input-l…
Robust and Computationally Efficient Linear Contextual Bandits under Adversarial Corruption and Heavy-Tailed Noise
Naoto Tani, Futoshi Futami
We study linear contextual bandits under adversarial corruption and heavy-tailed noise with finite -th moments for some . Existing work that addresses both adver…
Data-driven Projection Generation for Efficiently Solving Heterogeneous Quadratic Programming Problems
Tomoharu Iwata, Futoshi Futami
We propose a data-driven framework for efficiently solving quadratic programming (QP) problems by reducing the number of variables in high-dimensional QPs using instance-specific p…
-Regularized Empirical Risk Minimization Guarantees Small Smooth Calibration Error
Masahiro Fujisawa, Futoshi Futami
Calibration of predicted probabilities is critical for reliable machine learning, yet it is poorly understood how standard training procedures yield well-calibrated models. This wo…
Information-theoretic Generalization Analysis for VQ-VAEs: A Role of Latent Variables
Futoshi Futami, Masahiro Fujisawa
Latent variables (LVs) play a crucial role in encoder-decoder models by enabling effective data compression, prediction, and generation. Although their theoretical properties, such…
Uniform convergence of the smooth calibration error and its relationship with functional gradient
Futoshi Futami, Atsushi Nitanda
Calibration is a critical requirement for reliable probabilistic prediction, especially in high-risk applications. However, the theoretical understanding of which learning algorith…
PAC-Bayes Analysis for Recalibration in Classification
Masahiro Fujisawa, Futoshi Futami
Nonparametric estimation using uniform-width binning is a standard approach for evaluating the calibration performance of machine learning models. However, existing theoretical ana…
Information-theoretic Generalization Analysis for Expected Calibration Error
Futoshi Futami, Masahiro Fujisawa
While the expected calibration error (ECE), which employs binning, is widely adopted to evaluate the calibration performance of machine learning models, theoretical understanding o…
Time-Independent Information-Theoretic Generalization Bounds for SGLD
Futoshi Futami, Masahiro Fujisawa
We provide novel information-theoretic generalization bounds for stochastic gradient Langevin dynamics (SGLD) under the assumptions of smoothness and dissipativity, which are widel…
Information-theoretic Analysis of Test Data Sensitivity in Uncertainty
Futoshi Futami, Tomoharu Iwata
Bayesian inference is often utilized for uncertainty quantification tasks. A recent analysis by Xu and Raginsky 2022 rigorously decomposed the predictive uncertainty in Bayesian in…
Excess risk analysis for epistemic uncertainty with application to variational inference
Futoshi Futami, Tomoharu Iwata, Naonori Ueda +2
Bayesian deep learning plays an important role especially for its ability evaluating epistemic uncertainty (EU). Due to computational complexity issues, approximation methods such…
Loss function based second-order Jensen inequality and its application to particle variational inference
Futoshi Futami, Tomoharu Iwata, Naonori Ueda +2
Bayesian model averaging, obtained as the expectation of a likelihood function by a posterior distribution, has been widely used for prediction, evaluation of uncertainty, and mode…
Time-varying Gaussian Process Bandit Optimization with Non-constant Evaluation Time
Hideaki Imamura, Nontawat Charoenphakdee, Futoshi Futami +3
The Gaussian process bandit is a problem in which we want to find a maximizer of a black-box function with the minimum number of function evaluations. If the black-box function var…
Bayesian posterior approximation via greedy particle optimization
Futoshi Futami, Zhenghang Cui, Issei Sato +1
In Bayesian inference, the posterior distributions are difficult to obtain analytically for complex models such as neural networks. Variational inference usually uses a parametric…
Variational Inference based on Robust Divergences
Futoshi Futami, Issei Sato, Masashi Sugiyama
Robustness to outliers is a central issue in real-world machine learning applications. While replacing a model to a heavy-tailed one (e.g., from Gaussian to Student-t) is a standar…
Expectation Propagation for t-Exponential Family Using Q-Algebra
Futoshi Futami, Issei Sato, Masashi Sugiyama
Exponential family distributions are highly useful in machine learning since their calculation can be performed efficiently through natural parameters. The exponential family has r…