Research notebook

MathJax reference

List of posts:

Weekly summary 2018-11-10 (2018-11-07)
(CW17) Adversarial Examples Are Not Easily Detected - Bypassing Ten Detection Methods (2018-04-05)
Combinatory Categorial Grammar (2018-01-01): How we all speak in functions
Control theory (2017-12-24)
Learning grammar (2017-10-04)
Weekly summary 2017-09-09 (2017-09-05)
Theorem proving with modern ML (2017-09-05)
Annealed importance sampling (2017-07-20)
(HKY17) Hyperparameter Optimization - A Spectral Approach (2017-07-19)
(AR17) Provable benefits of representation learning (2017-07-18)
(AKV17) A sparse recovery view of sentence embeddings, bag of n-grams, and LSTMs (2017-07-18)
Weekly summary 2017-07-22 (2017-07-18)
(TPGB17) The space of transferable adversarial examples (2017-05-24)
Weekly summary 2017-04-29 (2017-04-25)
Adversarial thoughts (2017-04-16)
Inverse RL (2017-04-03)
Confidence in neural nets (2017-04-03)
Weekly summary 2017-04-08 (2017-04-03)
AAML workshop (2017-04-01)
Neural nets as kernel space (2017-03-23)
Weekly summary 2017-03-18 (2017-03-18)
Langevin dynamics (2017-03-15)
Learning to model structures and data (2017-03-12)
Stochastic calculus (2017-03-08)
Weekly summary 2017-03-11 (2017-03-07)
Brownian Motion (2017-03-07)
Tensorflow setup (2017-03-03)
Adversarial experiments (2017-03-02)
Neural net learning, Anthony and Bartlett (2017-02-28)
Conversation with Paul Christiano (2017-02-28)
AdaGAN (2017-02-24)
Multiplicative weights (2017-02-24)
Adversarial examples in neural networks (2017-02-21)
Weekly summary 2017-02-25 (2017-02-21)
Questions (2017-02-19)
UDT (2017-02-19)
The Blessing and the Curse of the Multiplicative Updates (2017-02-12)
Game theory and decision theory (2017-02-12)
Neural net separation (2017-02-09)
Boosting (2017-02-08)
Variational Bayes (2017-02-06)
Logical induction (2017-02-01)
Concrete problems in AI safety (2017-02-01)
Alignment for advanced machine learning systems (2017-02-01)
Linear convex regulator 2 (2017-01-10)
Arrows (2016-12-31)
Transfer learning (2016-12-29)
Kernels (2016-12-29)
(R16) How to calculate partition functions using convex programming hierarchies - provable bounds for variational methods (2016-12-28)
Legendre transform (2016-12-28)
Hierarchies of convex relaxations (2016-12-28)
GANs (2016-12-28)
(HMR16) Gradient descent learns linear dynamical systems (2016-12-27)
(HM16) A non-generative framework and convex relaxations for unsupervised learning (2016-12-27)
Free monads (2016-12-27)
Higher-order abstract syntax (2016-12-26)
Catamorphism (2016-12-26)
Neural nets in Haskell (2016-12-25)
Haskell extensions (2016-12-25)
Musings on Barron's Theorem (2016-12-22)
Weekly summary 2016-12-17 (2016-12-17)
Linear convex regulator (2016-12-14)
Weekly summary 2016-12-10 (2016-12-10)
Linear quadratic regulator (2016-12-09)
Control theory (2016-12-06)
Embedding methods in NLP (2016-12-06)
POMDPs (2016-11-29)
Weekly summary 2016-12-03 (2016-11-28)
Policy gradient (2016-11-22)
Weekly summary 2016-11-19 (2016-11-14)
Probabilistic models - Ideas (2016-11-07)
Weekly summary 2016-11-12 (2016-11-07)
Function approximation (2016-11-01)
Weekly summary 2016-11-05 (2016-10-31)
(MVB16) Geometry of Polysemy (2016-10-28)
RL references (2016-10-25)
Reinforcement learning convergence (2016-10-24)
Weekly summary 2016-10-29 (2016-10-24)
Reinforcement learning theory (2016-10-22)
Learning structured, robust, and multimodal deep models (2016-10-21)
Weekly summary 2016-10-22 (2016-10-19)
DL experiments (2016-10-17)
MDP's with continuous state space (scratch) (2016-10-14)
MDP's with continuous state space (2016-10-14)
Finite model theory (2016-10-14)
Language games (2016-10-13)
Alexa (2016-10-13)
Interpretable neural nets (2016-10-12)
Hidden Markov Models (2016-10-11)
Bandit convex optimization (2016-10-11)
Generalization of neural nets (2016-10-10)
Neural nets learn dictionaries (2016-10-10)
Weekly summary 2016-10-15 (2016-10-10)
Weekly summary 2016-10-08 (2016-10-08)
(WJ08) Graphical Models, Exponential Families, and Variational Inference (2016-09-30)
Reinforcement learning (2016-09-28)
(PMDH16) Convolutional Patch Representations for Image Retrieval - an Unsupervised Approach (2016-09-26)
Weekly summary 2016-10-01 (2016-09-26)
Semantic shared response (2016-09-24)
Weekly summary 2016-09-24 (2016-09-23)
DL generalization (2016-09-19)
Weekly summary 2016-09-17 (2016-09-19)
PCANet - A simple deep learning baseline for image classification? (2016-09-10)
(SV16) The mixing time of the Dikin walk in a polytope - a simple proof (2016-09-07)
LDA (Linear discriminant analysis) (2016-09-04)
Weekly summary 2016-09-10 (2016-09-04)
Transductive learning (2016-08-31)
Self-taught learning ([RBLPN07] Self-taught Learning - Transfer Learning from Unlabeled Data) (2016-08-31)
Nash equilibrium (2016-08-31)
Tensor decomposition (2016-08-30)
(BKS15) Dictionary Learning and Tensor Decomposition via the Sum-of-Squares Method (2016-08-30)
Ellipsoid method (2016-08-30)
Weekly summary 2016-09-03 (2016-08-30)
Matrix perturbation (2016-08-30)
Weekly summary 2016-08-27 (2016-08-27)
Interior point methods (2016-08-26)
Logic of provability (2016-08-25)
(CYHB13) Definability of Truth in Probabilistic Logic (2016-08-19)
Technical agenda (2016-08-19)
(SF15) Questions of reasoning under logical uncertainty (2016-08-19)
Lob's Theorem (2016-08-19)
Distribution of critical points (2016-08-13)
Weekly summary 2016-08-13 (2016-08-13)
(BH16) Algorithms for generalized topic modeling (2016-08-12)
Approximation theory and approximation practice (2016-08-08)
Weekly summary 2016-08-06 (2016-08-06)
Chebyshev polynomials (2016-08-04)
Neural net experiments (2016-08-03)
(HA16) Unsupervised Learning of Word-Sequence Representations from Scratch via Convolutional Tensor Decomposition (2016-08-02)
Convnets ideas (2016-08-02)
PMI for images (scratch) (2016-08-01)
PMI for images (2016-08-01)
High-dimensional probability (2016-08-01)
Types and programming languages, Benjamin Pierce (2016-07-31)
Type theory (2016-07-31)
LLVM tutorial (2016-07-31)
PMI and feature vectors (2016-07-29)
Representation learning (2016-07-28)
Complexity of neural networks (2016-07-25)
Tensorflow setup (2016-07-22)
Stanford quals (2016-06-29)
CART and random forests (2016-06-29)
k-means clustering (2016-06-28)
ICA (Independent components analysis) (2016-06-28)
Factor analysis (2016-06-28)
Linear dimensionality reduction ([CG15]) (2016-06-28)
CCA (Canonical correlation analysis) (2016-06-28)
(JSA15) Beating the Perils of Non-Convexity - Guaranteed Training of Neural Networks using Tensor Methods (2016-06-27)
(BGKP16) Non-negative matrix factorization under heavy noise (2016-06-27)
Relevant coordinates - Low-rank (2016-06-07)
Relevant coordinates (2016-06-02)
Inference for topic models - Code (2016-05-18)
(DKLPRS) Markov logic (2016-05-17)
Sampling (2016-05-17)
NLP 2016 Senior presentations (2016-05-14)
Weekly summary 5-14-16 (2016-05-11)
Towards a better understanding of streaming PCA (Yuanzhi Li) (2016-05-10)
Percy Liang's papers (2016-05-04)
NLP (2016-05-04)
LDC's - directions (2016-05-01)
Weekly summary 4-30-16 (2016-04-30)
Constrained optimization (2016-04-28)
Convexity (2016-04-23)
Convex problems (2016-04-23)
Second-order methods (2016-04-22)
NMF algorithm (2016-04-22)
Newcomb's Problem (2016-04-22)
Geometric functional analysis (2016-04-20)
Perfect LCCs (2016-04-13)
Notes index (2016-04-08)
Martingales (2016-04-08)
Matrix factorizations (2016-04-04)
(A16) Provable algorithms for inference in topic models (2016-04-04)
Weekly summary 4-9-16 (2016-04-04)
Maximum entropy distributions (2016-04-04)
Fisher information (2016-04-04)
Haskell (2016-04-03)
(AGM14) New algorithms for learning incoherent and overcomplete dictionaries (2016-04-02)
LCC lower bounds by geometry (2016-04-02)
(Bar13) Convexity of the image of a quadratic map via the relative entropy distance (2016-04-02)
Goemans-Williamson (2016-04-02)
Weekly summary 4-2-16 (2016-04-02)
Non-negative matrix factorization (2016-03-26)
(AGMM15) Simple, efficient, and neural algorithms for sparse coding (2016-03-25)
Sum of squares (2016-03-24)
Thoughts on LDC's (2016-03-21)
LSTM Programming (2016-03-19)
(ALLMR16) RAND-WALK - A latent variable model approach to word embeddings (2016-03-15)
(ALLMR16) Linear Algebraic Structure of Word Senses, with Applications to Polysemy (2016-03-15)
Thoughts on LDC's (2016-03-14)
Type and Cotype (2016-03-14)
Neural nets basics (2016-03-13)
(ALM16) WHY ARE DEEP NETS REVERSIBLE - A SIMPLE THEORY, WITH IMPLICATIONS FOR TRAINING (2016-03-13)
Interests (2016-03-13)
Matrix concentration (2016-03-13)
Spectral Bounds for Stochastic Diffusion Model in Networks (2016-03-08)
(CHMAL15) The Loss Surfaces of Multilayer Networks (2016-03-07)
(AO15) Linear coupling (2016-03-06)
Mirror descent (2016-03-05)
Accelerated Gradient descent (2016-03-05)
Analysis of neural networks (2016-03-05)
SGD Variance Reduction (2016-03-04)
SDP duality (2016-03-04)
Duality (2016-03-04)
Convex optimization (2016-03-04)
Gradient descent (2016-03-04)
(GRSY15) How Hard is Inference for Structured Prediction? (2016-03-03)
LDCs (2016-03-03)
Algorithms (2016-03-03)
Perron-Frobenius Theorem (2016-03-03)
(SD15) Minimax rates for memory-bounded sparse linear regression (2016-02-29)
Scraps (2016-02-29)
(Rem16) The Hilbert Function, Algebraic Extractors, and Recursive Fourier Sampling (2016-02-29)
Recursive Fourier Sampling (2016-02-29)
MAT529 notes (2016-02-29)
Censored block model (2016-02-28)
(MNS12) (2016-02-28)
Test (2016-02-27)
Real channels (2016-02-27)
Conversation with Zeev 2-24-16 (2016-02-27)
Calculus formulas (2016-02-27)
AI Control References (2016-02-27)