Minimax Optimal Online Stochastic Learning for Sequences of Convex Functions under Sub-Gradient Observation Failures
arXiv:1904.09369
Abstract
We study online convex optimization under stochastic sub-gradient observation faults, where we introduce adaptive algorithms with minimax optimal regret guarantees. We specifically study scenarios where our sub-gradient observations can be noisy or even completely missing in a stochastic manner. To this end, we propose algorithms based on sub-gradient descent method, which achieve tight minimax optimal regret bounds. When necessary, these algorithms utilize properties of the underlying stochastic settings to optimize their learning rates (step sizes). These optimizations are the main factor in providing the minimax optimal performance guarantees, especially when observations are stochastically missing. However, in real world scenarios, these properties of the underlying stochastic settings may not be revealed to the optimizer. For such a scenario, we propose a blind algorithm that estimates these properties empirically in a generally applicable manner. Through extensive experiments, we show that this empirical approach is a natural combination of regular stochastic gradient descent and the minimax optimal algorithms (which work best for randomized and adversarial function sequences, respectively).
arXiv comment25 pages, 6 figures, preprint, single column
References in corpus (7)
- Subspace Learning and Imputation for Streaming Big Data Matrices and Tensors
- Regularized Modified BPDN for Noisy Sparse Reconstruction with Partial Erroneous Support and Signal Value Knowledge
- Online Learning with Feedback Graphs: Beyond Bandits
- Online Categorical Subspace Learning for Sketching Big Data with Misses
- Threshold Effects in Parameter Estimation from Compressed Data
- (Bandit) Convex Optimization with Biased Noisy Gradient Oracles
- Online and Batch Learning Algorithms for Data with Missing Features