Towards Noise-adaptive, Problem-adaptive (Accelerated) Stochastic Gradient Descent
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2021
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912976687071232 |
|---|---|
| author | Vaswani, Sharan Dubois-Taine, Benjamin Babanezhad, Reza |
| author_facet | Vaswani, Sharan Dubois-Taine, Benjamin Babanezhad, Reza |
| contents | We aim to make stochastic gradient descent (SGD) adaptive to (i) the noise $σ^2$ in the stochastic gradients and (ii) problem-dependent constants. When minimizing smooth, strongly-convex functions with condition number $κ$, we prove that $T$ iterations of SGD with exponentially decreasing step-sizes and knowledge of the smoothness can achieve an $\tilde{O} \left(\exp \left( \frac{-T}κ \right) + \frac{σ^2}{T} \right)$ rate, without knowing $σ^2$. In order to be adaptive to the smoothness, we use a stochastic line-search (SLS) and show (via upper and lower-bounds) that SGD with SLS converges at the desired rate, but only to a neighbourhood of the solution. On the other hand, we prove that SGD with an offline estimate of the smoothness converges to the minimizer. However, its rate is slowed down proportional to the estimation error. Next, we prove that SGD with Nesterov acceleration and exponential step-sizes (referred to as ASGD) can achieve the near-optimal $\tilde{O} \left(\exp \left( \frac{-T}{\sqrtκ} \right) + \frac{σ^2}{T} \right)$ rate, without knowledge of $σ^2$. When used with offline estimates of the smoothness and strong-convexity, ASGD still converges to the solution, albeit at a slower rate. We empirically demonstrate the effectiveness of exponential step-sizes coupled with a novel variant of SLS. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2110_11442 |
| institution | arXiv |
| publishDate | 2021 |
| record_format | arxiv |
| spellingShingle | Towards Noise-adaptive, Problem-adaptive (Accelerated) Stochastic Gradient Descent Vaswani, Sharan Dubois-Taine, Benjamin Babanezhad, Reza Optimization and Control Machine Learning We aim to make stochastic gradient descent (SGD) adaptive to (i) the noise $σ^2$ in the stochastic gradients and (ii) problem-dependent constants. When minimizing smooth, strongly-convex functions with condition number $κ$, we prove that $T$ iterations of SGD with exponentially decreasing step-sizes and knowledge of the smoothness can achieve an $\tilde{O} \left(\exp \left( \frac{-T}κ \right) + \frac{σ^2}{T} \right)$ rate, without knowing $σ^2$. In order to be adaptive to the smoothness, we use a stochastic line-search (SLS) and show (via upper and lower-bounds) that SGD with SLS converges at the desired rate, but only to a neighbourhood of the solution. On the other hand, we prove that SGD with an offline estimate of the smoothness converges to the minimizer. However, its rate is slowed down proportional to the estimation error. Next, we prove that SGD with Nesterov acceleration and exponential step-sizes (referred to as ASGD) can achieve the near-optimal $\tilde{O} \left(\exp \left( \frac{-T}{\sqrtκ} \right) + \frac{σ^2}{T} \right)$ rate, without knowledge of $σ^2$. When used with offline estimates of the smoothness and strong-convexity, ASGD still converges to the solution, albeit at a slower rate. We empirically demonstrate the effectiveness of exponential step-sizes coupled with a novel variant of SLS. |
| title | Towards Noise-adaptive, Problem-adaptive (Accelerated) Stochastic Gradient Descent |
| topic | Optimization and Control Machine Learning |
| url | https://arxiv.org/abs/2110.11442 |