確率的多様性ウィンドウ:ロボティクス拡散サンプリングにおけるノイズ影響の診断
Stochastic Diversity Windows: Diagnosing Noise Influence in Robotic Diffusion Sampling
拡散モデルの各デノイズ時刻でノイズを変えた反事実診断を行い、出力への影響が強い区間(SDW)を特定。その区間を利用した多様性増幅と計算削減サンプラーを提案した。
詳しい要約
1. どんなもの?
2. 先行研究と比べてどこがすごい?
3. 技術・手法の肝は?
4. どうやって有効だと検証した?
5. 議論はある?
6. 次に読むべき論文は?
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Tina Lakhani, Jing Wu, Yu-Kun Lai, Ze Ji
分類: cs.RO, cs.LG
原文アブストラクト
Diffusion models are increasingly adopted in robotics and control due to their capability to express multiple feasible solutions to a given task. However, the role of stochasticity in the diffusion model-sampler across denoising remains poorly understood. We introduce a per-timestep counterfactual diagnostic that tests how changing the sampled noise affects the final output. Across five model-sampler configurations spanning three robotics benchmarks, diverse architectures, domains, and conditioning mechanisms, we reveal highly varied temporal sensitivity profiles, where noise-induced deviations can amplify, partially contract, or undergo near-total attenuation downstream. From these profiles, we define stochastic diversity windows (SDWs): compact intervals that identify where sampler stochasticity has the strongest measured influence on the final output. Guided by these windows, we apply two heuristic interventions: targeted stochastic amplification, which increases sample diversity exploration of the solution space, and an SDW-hybrid sampler, which replaces DDPM steps with DDIM skips in low-impact regions, resulting in network evaluation reductions of up to 40-60% and wall-clock time by up to 85%, with no consistent changes detected in feasibility, cost, or diversity across held-out tasks.
