Energy-based Autoregressive Generation for Neural Population Dynamics

TL;DR

This paper introduces an energy-based autoregressive framework for neural population dynamics that achieves high-quality synthetic neural data generation efficiently, with applications in neuroscience research and brain-computer interfaces.

Contribution

The novel EAG framework employs energy-based transformers for efficient, high-fidelity neural data modeling, outperforming diffusion methods and enabling conditional generation.

Findings

State-of-the-art generation quality on benchmark datasets

Significant computational efficiency improvements

Enhanced motor BCI decoding accuracy

Abstract

Understanding brain function represents a fundamental goal in neuroscience, with critical implications for therapeutic interventions and neural engineering applications. Computational modeling provides a quantitative framework for accelerating this understanding, but faces a fundamental trade-off between computational efficiency and high-fidelity modeling. To address this limitation, we introduce a novel Energy-based Autoregressive Generation (EAG) framework that employs an energy-based transformer learning temporal dynamics in latent space through strictly proper scoring rules, enabling efficient generation with realistic population and single-neuron spiking statistics. Evaluation on synthetic Lorenz datasets and two Neural Latents Benchmark datasets (MC_Maze and Area2_bump) demonstrates that EAG achieves state-of-the-art generation quality with substantial computational efficiency improvements, particularly over diffusion-based methods. Beyond optimal performance, conditional generation applications show two capabilities: generalizing to unseen behavioral contexts and improving motor brain-computer interface decoding accuracy using synthetic neural data. These results demonstrate the effectiveness of energy-based modeling for neural population dynamics with applications in neuroscience research and neural engineering. Code is available at https://github.com/NinglingGe/Energy-based-Autoregressive-Generation-for-Neural-Population-Dynamics.