I haven't gone around reading the blogs on the interweb in a while, here is the good stuff I have been missing
Table of Contents.
- Make It Happen. Reinforcement Learning as prescriptive analytics.
- Total Control. Reinforcement Learning as Optimal Control.
- The Linearization Principle. If a machine learning algorithm does crazy things when restricted to linear models, it’s going to do crazy things on complex nonlinear models too.
- The Linear Quadratic Regulator. A quick intro to LQR as why it is a great baseline for benchmarking Reinforcement Learning.
- A Game of Chance to You to Him Is One of Real Skill. Laying out the rules of the RL Game and comparing to Iterative Learning Control.
- The Policy of Truth. Policy Gradient is a Gradient Free Optimization Method.
- A Model, You Know What I Mean? Nominal control and the power of models.
- Updates on Policy Gradients. Can we fix policy gradient with algorithmic enhancements?
- Clues for Which I Search and Choose. Simple methods solve apparently complex RL benchmarks.
- Smoothed analysis for low-rank solutions to semidefinite programs in quadratic penalty form
- Another simple solution to the Basel problem
- Tight Frames and Approximation 2018
- Partisan gerrymandering with geographically compact districts
- An impossibility theorem for gerrymandering
- Monte Carlo approximation certificates for k-means clustering
- Optimal line packings from finite group actions
- Fundamental Limits of Weak Recovery with Applications to Phase Retrieval
- Talks from the Summer of ’17
- Limitations of Encoder-Decoder GAN architectures Sanjeev and Andrej
- Can increasing depth serve to accelerate optimization? Nadav
- Proving generalization of deep nets via compression Sanjeev
- Generalization Theory and Deep Nets, An introduction Sanjeev
- Tutorial on large deviation principles,
- Random Matrix Diagonalization on Computer
- Playing a bit with Julia
- Concentration without moments
- Around the circular law : erratum
- Back to basics – Bits of fluctuations
- k-server, part 3: entropy regularization for weighted k-paging
- k-server, part 2: continuous time mirror descent
- k-server, part 1: online learning and online algorithms
- Algorithms, Machine Learning, and Optimization: we are hiring!
On Nuit Blanche, we passed the 7 million page views "milestone", woohoo !
Liked this entry ? subscribe to Nuit Blanche's feed, there's more where that came from. You can also subscribe to Nuit Blanche by Email, explore the Big Picture in Compressive Sensing or the Matrix Factorization Jungle and join the conversations on compressive sensing, advanced matrix factorization and calibration issues on Linkedin.