8 citations · 8 across the 11 of their papers we have counts for
13 papers
Distortion of AI Alignment Revisited: RLHF is a Decent Utilitarian Aligner
Kazusato Oko, Annie Ulichney, Nika Haghtalab +1
While Reinforcement Learning from Human Feedback (RLHF) is the standard paradigm for aligning large language models with human preferences, its effectiveness in pluralistic setting…
When Does Metadata Conditioning (NOT) Work for Language Model Pre-Training? A Study with Context-Free Grammars
Rei Higuchi, Ryotaro Kawata, Naoki Nishikawa +7
The ability to acquire latent semantics is one of the key properties that determines the performance of language models. One convenient approach to invoke this ability is to prepen…
Direct Distributional Optimization for Provable Alignment of Diffusion Models
Ryotaro Kawata, Kazusato Oko, Atsushi Nitanda +1
We introduce a novel alignment method for diffusion models from distribution optimization perspectives while providing rigorous convergence guarantees. We first formulate the probl…
A Statistical Theory of Contrastive Pre-training and Multimodal Generative AI
Kazusato Oko, Licong Lin, Yuhang Cai +1
Multi-modal generative AI systems, such as those combining vision and language, rely on contrastive pre-training to learn representations across different modalities. While their p…
Pretrained transformer efficiently learns low-dimensional target functions in-context
Kazusato Oko, Yujin Song, Taiji Suzuki +1
Transformers can efficiently learn in-context from example demonstrations. Most existing theoretical analyses studied the in-context learning (ICL) ability of transformers for line…
Learning sum of diverse features: computational hardness and efficient gradient-based training for ridge combinations
Kazusato Oko, Yujin Song, Taiji Suzuki +1
We study the computational and sample complexity of learning a target function with additive structure, that is, $f_*(x) = \frac{1}{\sqrt{M}}\sum_{m…
Neural network learns low-dimensional polynomials with SGD near the information-theoretic limit
Jason D. Lee, Kazusato Oko, Taiji Suzuki +1
We study the problem of gradient descent learning of a single-index target function unde…
Flow matching achieves almost minimax optimal convergence
Kenji Fukumizu, Taiji Suzuki, Noboru Isobe +2
Flow matching (FM) has gained significant attention as a simulation-free generative model. Unlike diffusion models, which are based on stochastic differential equations, FM employs…
Symmetric Mean-field Langevin Dynamics for Distributional Minimax Problems
Juno Kim, Kakei Yamamoto, Kazusato Oko +2
In this paper, we extend mean-field Langevin dynamics to minimax optimization over probability distributions for the first time with symmetric and provably convergent updates. We p…
Primal and Dual Analysis of Entropic Fictitious Play for Finite-sum Problems
Atsushi Nitanda, Kazusato Oko, Denny Wu +2
The entropic fictitious play (EFP) is a recently proposed algorithm that minimizes the sum of a convex functional and entropy in the space of measures -- such an objective naturall…
Diffusion Models are Minimax Optimal Distribution Estimators
Kazusato Oko, Shunta Akiyama, Taiji Suzuki
While efficient distribution learning is no doubt behind the groundbreaking success of diffusion modeling, its theoretical guarantees are quite limited. In this paper, we provide t…
Versatile Single-Loop Method for Gradient Estimator: First and Second Order Optimality, and its Application to Federated Learning
Kazusato Oko, Shunta Akiyama, Tomoya Murata +1
While variance reduction methods have shown great success in solving large scale optimization problems, many of them suffer from accumulated errors and, therefore, should periodica…
Nearly Tight Spectral Sparsification of Directed Hypergraphs by a Simple Iterative Sampling Algorithm
Kazusato Oko, Shinsaku Sakaue, Shin-ichi Tanigawa
Spectral hypergraph sparsification, an attempt to extend well-known spectral graph sparsification to hypergraphs, has been extensively studied over the past few years. For undirect…