6 papers · 1 filter
Reinforcement Learning for Hierarchical Reasoning Rewards: Minimax-Optimal Rates with Transformers
Naoki Nishikawa, Taiji Suzuki
Reinforcement learning (RL) has become a standard tool for post-training language models on reasoning tasks, where the policy is updated by reward feedback while exploring the spac…
Escaping Iterative Parameter-Space Noise: Differentially Private Learning with a Hypernetwork
Naoki Nishikawa, Shokichi Takakura, Satoshi Hasegawa
Differentially private (DP) training of neural networks is often hindered by the large amount of noise required by gradient-based methods such as DP-SGD, which repeatedly inject hi…
Dataset Distillation Efficiently Encodes Low-Dimensional Representations from Gradient-Based Learning of Non-Linear Tasks
Yuri Kinoshita, Naoki Nishikawa, Taro Toyoizumi
Dataset distillation, a training-aware data compression technique, has recently attracted increasing attention as an effective tool for mitigating costs of optimization and data st…
From Shortcut to Induction Head: How Data Diversity Shapes Algorithm Selection in Transformers
Ryotaro Kawata, Yujin Song, Alberto Bietti +4
Transformers can implement both generalizable algorithms (e.g., induction heads) and simple positional shortcuts (e.g., memorizing fixed output positions). In this work, we study h…
Degrees of Freedom for Linear Attention: Distilling Softmax Attention with Optimal Feature Efficiency
Naoki Nishikawa, Rei Higuchi, Taiji Suzuki
Linear attention has attracted interest as a computationally efficient approximation to softmax attention, especially for long sequences. Recent studies have explored distilling so…
Mixture of Experts Provably Detect and Learn the Latent Cluster Structure in Gradient-Based Learning
Ryotaro Kawata, Kohsei Matsutani, Yuri Kinoshita +2
Mixture of Experts (MoE), an ensemble of specialized models equipped with a router that dynamically distributes each input to appropriate experts, has achieved successful results i…