Aggregated Momentum: Stability Through Passive Damping

Momentum is a simple and widely used trick which allows gradient-based optimizers to pick up speed in low curvature directions. Its performance depends crucially on a damping coefficient β. Large β values can potentially deliver much larger speedups, but are prone to oscillations and instability; hence one typically resorts to small values such as 0.5 or 0.9. We propose Aggregated Momentum (AggMo), a variant of momentum which combines multiple velocity vectors with different β parameters. AggMo is trivial to implement, but significantly dampens oscillations, enabling it to remain stable even for aggressive β values such as 0.999. We reinterpret Nesterov’s accelerated gradient descent as a special case of AggMo and provide theoretical convergence bounds for online convex optimization. Empirically, we find that AggMo is a suitable drop-in replacement for other momentum methods, and frequently delivers faster convergence.