Mixture Density Networks

Also known as MDN

Follow this topic Ask about this topic

Latest papers

9 papers1 paper in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

Energy-Score Stabilized Attentive Mixture-Density Policy: A Lightweight Approach to Multimodal Robot Motion
Oct 18, 2026Sachiya Fujita, Hideyuki Ichiwara, Shigeki Sugano +1Visuomotor Policy Learning Mixture Density Networks
All authors are with the Waseda University, Shinjuku, 169-8555 Tokyo, Japan.
FlipToSee: A Probabilistic Stable Placement Prior for Active Visual Exploration via Regrasping
Sep 17, 2026Chang Shu, Sushil Samuel Dinesh, Shinkyu ParkMixture Density Networks Active Visual Perception
Electrical and Computer Engineering, King Abdullah University of Science and Technology (KAUST), Thuwal, 23955-6900, Saudi Arabia
Heads, Not Backbones: Output Heads Dominate Architectures on Fat-Tailed Returns
Jun 29, 2026Sichao He, Yansong ZhangMixture Density Networks Quantitative Finance
Peking University · Academy for Advanced Interdisciplinary Studies · Beijing, China +2
AeroCast: Probabilistic 3D Trajectory Prediction for Non-Cooperative Aerial Obstacles via Transformer-MDN Architecture
Jun 23, 2026Syed Izzat Ullah, Jose BacaProbabilistic Trajectory Prediction Aerial Robotics
Department of Engineering, Texas A&M University–Corpus Christi, Corpus Christi, TX 78412 USA
Probabilistic Salary Prediction with Graph Attention Networks and a Mixture Density Network
Jun 10, 2026Zhipei Qin, Mohammad Shokri, N. van Weeren +1Mixture Density Networks Tabular Prediction
Leiden Institute of Advanced Computer Science (LIACS) · Randstad N.V.
Modeling Depth Ambiguity: A Mixture-Density Representation for Flying-Point-Free Depth Estimation
Jun 1, 2026Siyuan Bian, Congrong Xu, Jun GaoMixture Density Networks Depth Estimation
University of Michigan · NVIDIA
A Mutual Information Lower Bound for Multimodal Regression Active Learning
May 14, 2026Leonardo Ferreira Guilhoto, Akshat Kaushal, Paris PerdikarisMixture Density Networks Active Learning
Graduate Group on Applied Mathematics & Computational Science · Department of Computer and Information Science University of Pennsylvania Philadelphia, PA 19104 · Department of Mechanical Engineering and Applied Mechanics University of Pennsylvania Philadelphia, PA 19104
Liquid Networks with Mixture Density Heads for Efficient Imitation Learning
Mar 28, 2026Nikolaus CorrellMixture Density Networks Imitation Learning
University of Colorado Boulder
A Distribution-to-Distribution Neural Probabilistic Forecasting Framework for Dynamical Systems
Mar 26, 2026Tianlin Yang, Hailiang Du, Louis AslettMixture Density Networks Probabilistic Time Series Forecasting
Department of Mathematical Sciences, Durham University, Durham DH1 3LE, United Kingdom · School of Mathematics, East China University of Science and Technology, Shanghai 200237, China · Data Science Institute, The London School of Economics and Political Science, London WC2A 2AE, United Kingdom

Oct 18, 2026J/K move · Enter open · S save

Energy-Score Stabilized Attentive Mixture-Density Policy: A Lightweight Approach to Multimodal Robot Motion

Sachiya Fujita, Hideyuki Ichiwara, Shigeki Sugano, Tetsuya Ogata

All authors are with the Waseda University, Shinjuku, 169-8555 Tokyo, Japan.

Visuomotor Policy Learning Mixture Density Networks Data-Efficient Robot Learning Multimodal Trajectory Prediction

Open paper AskPDF arXiv

For practical motion generation, it is essential to handle multimodality (multiple actions can be correct for the same observation) while maintaining low inference cost and strong generalization from limited demonstrations. We introduce an attentive mixture-density policy trained with the Energy Score that represents future visuomotor trajectories as explicit probability distributions with a single forward pass. Concretely, we output Gaussian mixture parameters for joint commands (and optionally attention points) and optimize them with the Energy Score (computed as a sum of 1D CRPS under a diagonal covariance assumption) instead of the negative log-likelihood (NLL) to avoid MDN singularities and gradient-scale instabilities. Our architecture couples explicit spatial attention with mixture-density outputs, enabling robust multimodal behavior selection under visual noise and small-data regimes. On an 8-DOF manipulator, the method generates distinct avoidance trajectories and stabilizes learning in obstacle avoidance. Moreover, in a randomized moving-object grasping task, where spatiotemporal multimodality and fast timing decisions are required, the proposed model outperforms Diffusion Policy by 15-25% under several unseen conditions, demonstrating superior generalization and real-time feasibility.