- Indexing by Latent Semantic Analysis
- The Latent Semantic Analysis Theory of Acquisition, Induction, and Representation of Knowledge
- word2vec Explained: Deriving Mikolov et al.’s Negative-Sampling Word-Embedding Method
- Stability and Generalization
- Adaptive Subgradient Methods for Online Learning and Stochastic Optimization
- The Method of projections for finding the common point of convex sets
- A semismooth newton method for fast, generic convex programming
- SuperMann: A superlinearly convergent algorithm for finding fixed points of nonexpansive operators
- On projection algorithms for solving convex feasibility problems
- Monotone operator methods
- Distributed optimization and statistical learning via the alternating directions method of multipliers
- Line search for averaged operator iteration
- A Convex Optimization Approach to Radiation Treatment Planning with Dose Constraints
- The idea behind Krylov methods
- Densely Connected Convolutional Networks
- Learning from Simulated and Unsupervised Images through Adversarial Training
- Computational Imaging on the Electric Grid
- Convexified Convolutional Neural Networks
- Feynman's lecture on quantum computers (https://people.eecs.berkeley.edu/~christos/classics/Feynman.pdf)
- ANDERSON ACCELERATION FOR FIXED-POINT ITERATIONS
- Two Classes of Multisecant Methods for Nonlinear Acceleration
- ADAM: A METHOD FOR STOCHASTIC OPTIMIZATION
- Multi-Period Trading via Convex Optimization (http://stanford.edu/~boyd/papers/cvx_portfolio.html)
- Breaking the Curse of Dimensionality with Convex Neural Networks
- A Tutorial on Bayesian Optimization of Expensive Cost Functions, with Application to Active User Modeling and Hierarchical Reinforcement Learning [https://arxiv.org/pdf/1012.2599.pdf]
- https://people.eecs.berkeley.edu/~jshun/thesis.pdf
- A practical guide to CNNs and Fisher Vectors for image instance retrieval
- SAGA: A Fast Incremental Gradient Method With Support for Non-Strongly Convex Composite Objectives
- Stochastic Dual Coordinate Ascent Methods for Regularized Loss Minimization
- Accelerating Stochastic Gradient Descent using Predictive Variance Reduction
- http://www.cds.caltech.edu/~doyle/hot/SDPrelaxations.pdf
- Occupy the Cloud: Distributed Computing for the 99% (PyWren)
- Improving Efficiency and Scalability of Sum of Squares Optimization: Recent Advances and Limitations
- NP-hardness of deciding convexity of quartic polynomials and related problems
- Tractable fitting with convex polynomials via sum-of-squares
- LAGRANGE MULTIPLIERS AND OPTIMALITY
- Mastering the game of Go without human knowledge
- Interior-point methods for optimization (Nemirovski and Todd)
- Convergence rate of incremental aggregated gradient algorithms (Pablo Parrilo)
- Towards Generalization and Simplicity in Continuous Control (kakade)
- Stochastic subgradient method converges on tame functions (kakade) (https://arxiv.org/pdf/1804.07795.pdf)
- Lifted Neural Networks (El Ghaoui)
- Minimizing Finite Sums with the Stochastic Average Gradient (Shmidt)
- How to escape saddle points efficiently (jordan)
- Local Minima and Convergence in Low-Rank Semidefinite Programming (Burer, Monteiro)
- The non-convex Burer-Monteiro approach works on smooth semidefinite programs (Boumal)
- Fast Exact Multiplication by the Hessian (Pearlmutter 1994)
- The geometry of graphs and some of its algorithmic applications [LLR '94]
- Expander Flows, Geometric Embeddings and Graph Partitioning [Arora 09]
- Representation Tradeoffs for Hyperbolic Embeddings
- improving distributional similarity with lessons learned from word embeddings
- A La Carte Embedding: Cheap but Effective Induction of Semantic Feature Vectors
- A CONVERGENCE ANALYSIS OF GRADIENT DESCENT FOR DEEP LINEAR NEURAL NETWORKS
- Computational Complexity, NP Completeness and Optimization Duality: A Survey
- Bundle Methods for Regularized Risk Minimization (related to reducing convex programs to LPs)
- Solving standard quadratic optimization problems via semidefinite and copositive programming (convex program that is NP-hard via copositive programming, https://www.ti.inf.ethz.ch/ew/lehre/ApproxSDP09/notes/copositive.pdf)
- An Exact duality Theory for Semidefinite Programming and its Complexity Implications (strong duality without assumptions(?!))
- Notes on interior-point methods by Matousek (https://www.ti.inf.ethz.ch/ew/lehre/ApproxSDP09/notes/interior.pdf)
- Duality for SOCPs (https://people.eecs.berkeley.edu/~elghaoui/Teaching/EE227A/lecture10.pdf)
- Interior-point methods for optimization* Copositive Programming – a Survey* The Supporting Halfspace--Quadratic Programming Strategy for the Dual of the Best Approximation Problem (SJO)