Timezone: »

Particle Dual Averaging: Optimization of Mean Field Neural Network with Global Convergence Rate Analysis
Atsushi Nitanda · Denny Wu · Taiji Suzuki

Wed Dec 08 04:30 PM -- 06:00 PM (PST) @ Virtual

We propose the particle dual averaging (PDA) method, which generalizes the dual averaging method in convex optimization to the optimization over probability distributions with quantitative runtime guarantee. The algorithm consists of an inner loop and outer loop: the inner loop utilizes the Langevin algorithm to approximately solve for a stationary distribution, which is then optimized in the outer loop. The method can be interpreted as an extension of the Langevin algorithm to naturally handle nonlinear functional on the probability space. An important application of the proposed method is the optimization of neural network in the mean field regime, which is theoretically attractive due to the presence of nonlinear feature learning, but quantitative convergence rate can be challenging to obtain. By adapting finite-dimensional convex optimization theory into the space of measures, we not only establish global convergence of PDA for two-layer mean field neural networks under more general settings and simpler analysis, but also provide quantitative polynomial runtime guarantee. Our theoretical results are supported by numerical simulations on neural networks with reasonable size.

Author Information

Atsushi Nitanda (Kyushu Institute of Technology / RIKEN)
Denny Wu (University of Toronto & Vector Institute)
Taiji Suzuki (The University of Tokyo/RIKEN-AIP)

More from the Same Authors