Course literature
Book references
-
Nocedal and S. Wright. Numerical optimization. Springer Science & Business Media, 2006.
-
Y. Nesterov. Introductory lectures on convex optimization: A basic course, volume 87. Springer Science & Business Media, 2013.
-
S. Boyd and L. Vandenberghe. Convex optimization. Cambridge university press, 2004.
-
D. Bertsekas. Convex optimization algorithms. Athena Scientific Belmont, 2015.
-
S. Bubeck. Convex optimization: Algorithms and complexity. Foundations and Trends in Machine Learning, 8(3-4):231–357, 2015.
Papers
- Efficient Projections onto the l1-Ball for Learning in High Dimensions
- Stay on path: PCA along graph paths
- CUR matrix decompositions for improved data analysis
- Simple and Deterministic Matrix Sketching
- Provable deterministic leverage score sampling
- EigenGame: PCA as a Nash equilibrium
- Linear convergence of gradient and proximal-gradient methods under the Polyak-Łojasiewicz condition
- Conditional Gradient Algorithms for Rank-One Matrix Approximations with a Sparsity Constraint
- Frank-Wolfe with Subsampling Oracle
- Linear convergence of a Frank-Wolfe type algorithm over trace-norm balls
- Large-Scale Distributed Second-Order Optimization Using Kronecker-Factored Approximate Curvature for Deep Convolutional Neural Networks
- Deep learning via Hessian-free optimization
- Adaptive Restart for Accelerated Gradient Schemes
- Why momentum really works
- A geometric alternative to Nesterov’s accelerated gradient descent
- A variational perspective on accelerated methods in optimization
- Large scale machine learning with SGD
- Accelerating SGD using predictive variance reduction
- Coordinate descent algorithms
- Stochastic Gradient Descent, Weighted Sampling, and the Randomized Kaczmarz algorithm
- On the importance of initialization and momentum in deep learning
- CoSaMP: Iterative signal recovery from incomplete and inaccurate samples
- Compressed sensing using generative models
- A Nearly-Linear Time Framework for graph-structured sparsity
- Deep image prior