17 citations · 48 across the 26 of their papers we have counts for
30 papers
Value-Rectified Distillation for Flow-based Offline Reinforcement Learning
Ke Jiang, Wen Jiang, Yoshinobu Kawahara +1
We aim to address the problem of Out-of-Distribution (OOD) Mode Averaging, a critical problem that emerges when distilling Flow Matching (FM) based behavior policies in offline Rei…
Invariant-Measure Reasoners: Stable Representations for Latent Reasoning
Yuto Inui, Takuya Konishi, Yoshinobu Kawahara
Latent reasoning models repeatedly update a latent state using the same recurrent block. As the recurrent depth increases, the sequence of latent states may converge to a compact s…
Causal Representation Learning with Instantaneous and Lagged Relations via Nonstationarity
Tatsuya Yamada, Hiroshi Morioka, Yoshinobu Kawahara
Causal representation learning for time-series data aims to identify latent states and their causal relations from observations. In this setting, an important challenge is to model…
Robust data-driven discovery of fractional differential equations via weak formulations and Pareto-based subset selection
Pongpisit Thanasutives, Yoshinobu Kawahara
Fractional partial differential equations describe nonlocal dynamics, but discovering them from noisy data is difficult because fractional differentiation amplifies high-frequency…
Dynamics-aware identification of governing equations from sparse and noisy data
Pongpisit Thanasutives, Yoshinobu Kawahara
Sparse identification of nonlinear dynamics (SINDy) and PDE functional identification (PDE-FIND) recover parsimonious ordinary and partial differential equations (ODEs and PDEs) fr…
Timesteps of Mamba Align with Human Reading Times
Yuji Yamamoto, Shinnosuke Isono, Yoshinobu Kawahara +1
This study demonstrates an alignment of per-word processing time in a popular state-space language model Mamba and human readers. In Mamba, the recurrent state transition at each l…
Structured Noise Adaptation for Sequential Bayesian Filtering with Embedded Latent Transfer Operators
Naichang Ke, Pongpisit Thanasutives, Yoshinobu Kawahara
Kalman filters based on the Embedded Latent Transfer Operators (ELTO) emerge as novel statistical tools for sequential state estimation. However, a critical limitation stems from t…
Deep Spectral Learning of Embedded Latent Transfer Operators for Stochastic Dynamical Systems
Ryogo Tanaka, Yoshinobu Kawahara
We propose a spectral learning method for stochastic nonlinear dynamical systems represented with embedded latent transfer operators in deep feature spaces. We instantiate the meth…
Mesh Field Theory: Port-Hamiltonian Formulation of Mesh-Based Physics
Satoshi Noguchi, Yoshinobu Kawahara
We present Mesh Field Theory (MeshFT) and its neural realization, MeshFT-Net: a structure-preserving framework for mesh-based continuum physics that cleanly separates the physics'…
Physics-inspired transformer quantum states via latent imaginary-time evolution
Kimihiro Yamazaki, Itsushi Sakata, Takuya Konishi +1
Neural quantum states (NQS) are powerful ansätze in the variational Monte Carlo framework, yet their architectures are often treated as black boxes. We propose a physically transpa…
Dualformer: Time-Frequency Dual Domain Learning for Long-term Time Series Forecasting
Jingjing Bai, Yoshinobu Kawahara
Transformer-based models, despite their promise for long-term time series forecasting (LTSF), suffer from an inherent low-pass filtering effect that limits their effectiveness. Thi…
Data-driven simulator of multi-animal behavior with unknown dynamics via offline and online reinforcement learning
Keisuke Fujii, Kazushi Tsutsui, Yu Teshima +6
Simulators of animal movements play a valuable role in studying behavior. Advances in imitation learning for robotics have expanded possibilities for reproducing human and animal m…
Wavy Transformer
Satoshi Noguchi, Yoshinobu Kawahara
Transformers have achieved remarkable success across natural language processing (NLP) and computer vision (CV). However, deep transformer models often suffer from an over-smoothin…
Intrinsic frequency distribution characterises neural dynamics
Ryohei Fukuma, Yoshinobu Kawahara, Okito Yamashita +3
Decomposing multivariate time series with certain basic dynamics is crucial for understanding, predicting and controlling nonlinear spatiotemporally dynamic systems such as the bra…
Explorative Curriculum Learning for Strongly Correlated Electron Systems
Kimihiro Yamazaki, Takuya Konishi, Yoshinobu Kawahara
Recent advances in neural network quantum states (NQS) have enabled high-accuracy predictions for complex quantum many-body systems such as strongly correlated electron systems. Ho…
Learning Stochastic Nonlinear Dynamics with Embedded Latent Transfer Operators
Naichang Ke, Ryogo Tanaka, Yoshinobu Kawahara
We consider an operator-based latent Markov representation of a stochastic nonlinear dynamical system, where the stochastic evolution of the latent state embedded in a reproducing…
Change-Point Detection in Industrial Data Streams based on Online Dynamic Mode Decomposition with Control
Marek Wadinger, Michal Kvasnica, Yoshinobu Kawahara
We propose a novel change-point detection method based on online Dynamic Mode Decomposition with control (ODMDwC). Leveraging ODMDwC's ability to find and track linear approximatio…
SiT: Symmetry-Invariant Transformers for Generalisation in Reinforcement Learning
Matthias Weissenbacher, Rishabh Agarwal, Yoshinobu Kawahara
An open challenge in reinforcement learning (RL) is the effective deployment of a trained policy to new or slightly different situations as well as semantically-similar environment…
The Disappearance of Timestep Embedding in Modern Time-Dependent Neural Networks
Bum Jun Kim, Yoshinobu Kawahara, Sang Woo Kim
Dynamical systems are often time-varying, whose modeling requires a function that evolves with respect to time. Recent studies such as the neural ordinary differential equation pro…
Glocal Hypergradient Estimation with Koopman Operator
Ryuichiro Hataya, Yoshinobu Kawahara
Gradient-based hyperparameter optimization methods update hyperparameters using hypergradients, gradients of a meta criterion with respect to hyperparameters. Previous research use…
Fast, accurate, and interpretable decoding of electrocorticographic signals using dynamic mode decomposition
Ryohei Fukuma, Kei Majima, Yoshinobu Kawahara +4
Dynamic mode (DM) decomposition decomposes spatiotemporal signals into basic oscillatory components (DMs). DMs can improve the accuracy of neural decoding when used with the nonlin…
Adaptive action supervision in reinforcement learning from real-world multi-agent demonstrations
Keisuke Fujii, Kazushi Tsutsui, Atom Scott +3
Modeling of real-world biological multi-agents is a fundamental problem in various scientific and engineering fields. Reinforcement learning (RL) is a powerful framework to generat…
Estimating counterfactual treatment outcomes over time in complex multiagent scenarios
Keisuke Fujii, Koh Takeuchi, Atsushi Kuribayashi +3
Evaluation of intervention in a multiagent system, e.g., when humans should intervene in autonomous driving systems and when a player should pass to teammates for a good shot, is c…
Learning interaction rules from multi-animal trajectories via augmented behavioral models
Keisuke Fujii, Naoya Takeishi, Kazushi Tsutsui +10
Extracting the interaction rules of biological agents from movement sequences pose challenges in various domains. Granger causality is a practical framework for analyzing the inter…