Linear Convergence of Gradient Methods for Estimating Structured Transition Matrices in High-dimensional Vector Autoregressive Models
Dec 6, 2021
Speakers
About
In this paper, we present non-asymptotic optimization guarantees of gradient descent methods for estimating structured transition matrices in high-dimensional vector autoregressive (VAR) models. We adopt the projected gradient descent (PGD) for single-structured transition matrices and the alternating projected gradient descent (AltPGD) for superposition-structured ones. Our analysis demonstrates that both gradient algorithms converge linearly to the statistical error even though the strong convexity of the objective function is absent under the high-dimensional settings. Moreover our result is sharp (up to a constant factor) in the sense of matching the phase transition theory of the corresponding model with independent samples. To the best of our knowledge, this analysis constitutes first non-asymptotic optimization guarantees of the linear rate for regularized estimation in high-dimensional VAR models. Numerical results are provided to support our theoretical analysis.In this paper, we present non-asymptotic optimization guarantees of gradient descent methods for estimating structured transition matrices in high-dimensional vector autoregressive (VAR) models. We adopt the projected gradient descent (PGD) for single-structured transition matrices and the alternating projected gradient descent (AltPGD) for superposition-structured ones. Our analysis demonstrates that both gradient algorithms converge linearly to the statistical error even though the strong conv…
Organizer
NeurIPS 2021
Account · 1.9k followers
About NeurIPS 2021
Neural Information Processing Systems (NeurIPS) is a multi-track machine learning and computational neuroscience conference that includes invited talks, demonstrations, symposia and oral and poster presentations of refereed papers. Following the conference, there are workshops which provide a less formal setting.
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
Lifting the veil on hyper-parameters for value-based deep reinforcement learning
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Multi-Step Budgeted Bayesian Optimization with Unknown Evaluation Costs
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
The Consequences of Massive Scaling in Machine Learning
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Learning Meaningful Representations of Life (LMRL)
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Aligned Structured Sparsity Learning for Efficient Image Super-Resolution
Watch later
Yulun Zhang, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Human-in-the-loop for a Disconnection Aware Retrosynthesis
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%