Finds in arxiv, october

This is duplication of my ongoing G+ series of post on interesting for me papers in arxiv. Older posts are not here but in my G+ thread.

Finds in #arxiv :
*Optimization, numerical & convex, ML*
The Linearized Bregman Method via Split Feasibility Problems: Analysis and Generalizations
Reformulation of  Split Bregman/ ADMM as split feasibility problem and algorithm/convergence for generalized split feasibility by Bregman projection. This general formulation include both Split Bregman and Kaczmarz (my comment – randomized Kaczmarz  seems could be here too)
http://arxiv.org/abs/1309.2094

Stochastic gradient descent and the randomized Kaczmarz algorithm
Hybrid of  randomized Kaczmarz  and stochastic gradient descent  – into my “to read” pile
http://arxiv.org/abs/1310.5715

Trust–Region Problems with Linear Inequality Constraints: Exact SDP Relaxation, Global Optimality and Robust Optimization
“Extended” trust region for linear inequalities constrains
http://arxiv.org/abs/1309.3000

Conic Geometric Programming
Unifing framwork for conic and geometric programming
http://arxiv.org/abs/1310.0899
http://en.wikipedia.org/wiki/Geometric_programming
http://en.wikipedia.org/wiki/Conic_programming

Gauge optimization, duality, and applications
Another big paper about different, not Lagrange duality, introduced by Freund (1987)
http://arxiv.org/abs/1310.2639

Color Bregman TV
mu parameters in split bregman made adaptive, to exploit coherence of edges in different color channels
http://arxiv.org/abs/1310.3146

Iteration Complexity Analysis of Block Coordinate Descent Methods
Some convergence analysis for BCD and projected gradient BCD
http://arxiv.org/abs/1310.6957

Successive Nonnegative Projection Algorithm for Robust Nonnegative Blind Source Separation
Nonnegative matrix factorization
http://arxiv.org/abs/1310.7529

Scaling SVM and Least Absolute Deviations via Exact Data Reduction
SVN for large-scale problems
http://arxiv.org/abs/1310.7048

Image Restoration using Total Variation with Overlapping Group Sparsity
While title is promising I have doubt about that paper.  The method authors suggest is equivalent to adding averaging filter to TV-L1 under L1 norm. There is no comparison  to just applying TV-L1 and smoothing filter interchangeably.The method author suggest is very costly, and using median filter instead of averaging would cost the same while obviously more robust.
http://arxiv.org/abs/1310.3447

*Deep learning*
Deep and Wide Multiscale Recursive Networks for Robust Image Labeling
_Open source_ matlab/c package coming soon(not yet available)
http://arxiv.org/abs/1310.0354

Improvements to deep convolutional neural networks for LVCSR
convolutional  networks, droput for speech recognition,
http://arxiv.org/abs/1309.1501v1

DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
Already discussed on G+  – open source framework in “learn one use everywhere” stile. Learning done off-line on GPU using ConvNet, and recognition is online in pure python.
http://arxiv.org/abs/1310.1531

Statistical mechanics of complex neural systems and high dimensional data
Big textbook-like overview paper on statistical mechanics of learning. I’ve put it in my “to read” pile.
http://arxiv.org/abs/1301.7115

Randomized co-training: from cortical neurons to machine learning and back again
“Selectron” instead of perception – neurons are “specializing” with weights.
http://arxiv.org/abs/1310.6536

Provable Bounds for Learning Some Deep Representations
http://arxiv.org/abs/1310.6343
Citation:”The current paper presents both an interesting family of denoising autoencoders as

well as new algorithms to provably learn almost all models in this family.”

*Computer vision*
Online Unsupervised Feature Learning for Visual Tracking
Sparse representation, overcomplete dictionary
http://arxiv.org/abs/1310.1690

From Shading to Local Shape
Shape restoration from local shading – could be very useful in low-feature environment.
http://arxiv.org/abs/1310.2916

Fast 3D Salient Region Detection in Medical Images using GPUs
Finding interest point in 3D images
http://arxiv.org/abs/1310.6736

Object Recognition System Design in Computer Vision: a Universal Approach
Grid-based universal framework for object detection/classification
http://arxiv.org/abs/1310.7170

Gaming :)
Lyapunov-based Low-thrust Optimal Orbit Transfer: An approach in Cartesian coordinates
For space sim enthusiast :)
http://arxiv.org/abs/1310.4201

ConvNet for windows

I have seen an excellent wlakthrough on building Alex Krizhevsky’s cuda-convnet for windows, but difference in configuration and installed packages could be tiresome. So here is complete build of convnet for windows 64:

https://github.com/s271/win_convnet

It require having CUDA compute capability 2.0 or better GPU of cause, Windows 64bit, Visual Studio 64bits and Python 64bit with NumPy installed. The rest of libs and dlls are precomplied. In building it I’ve followed instructions by Yalong Bai (Wyvernbai) from http://www.asiteof.me/archives/50.

Read Readme.md before installation – you may (or may not) require PYTHONPATH environmental variable set.

On side note I’ve used WinPython for both libraries and running the package. WinPython seems a very nice package, which include Spyder IDE. I have some problems with Spyder though – sometimes it behave erratically during debugging/running the code. Could be my inexperience with Spyder though. Another nice package – PythonXY – regretfully can not be used – it has only 32 bit version and will not compile with/run 64 bit modules.