NVIDIA GPU Grant Scheme

I really need to get around to writing on here more often…

Anyway, the NVIDIA GPU Grant Scheme has re-opened after a little break over Christmas and is now giving away Titan V (Volta) GPUs to academics. I was lucky enough to bag one of these earlier this week, so I’m eagerly awaiting the delivery! All that’s required is a 2000 word explanation of why it would be helpful to your research, so it’s well worth your time.

 

 

The Titan V is a significant upgrade to their previous offering in that the Titan V has 640 “Tensor cores” in addition to the usual CUDA cores. The tensor cores are dedicated to performing matrix multiplies using half precision arithmetic (though the input and output matrices can be single precision). There is a more detailed explanation of their use here. Using half precision on dedicated hardware components means a dramatic increase in speed for these operations, which are at the heart of neural network training.

The downside to using half precision arithmetic is the potential loss of accuracy in the result, depending upon the accumulation of rounding errors. Whilst this isn’t a huge problem for small matrix multiplications, using half precision for other matrix problems such as inversion will – essentially – multiply this error by the condition number of the matrix. At this point we can quickly run into problems! Nick Higham recently touched upon these topics in this blog post.

Summary of the MRC / NHS Digital Roadshow, York, Jan 2018

It’s now been six months since I switched from maths to healthcare (Wow, time goes fast!) and I’m starting to understand the bigger picture of funding bodies, legislative restrictions, and government-affiliated organisations in the area.

Two of these bodies are the MRC (Medical Research Council) and NHS Digital (owners of most secondary care datasets), so I was keen to attend their “roadshow” event in York. The event outlined some of the major upcoming changes to the healthcare domain over the next few years, mainly arising from the EUs data protection law, GDPR. I’ve summarised some of the key points below whilst the slides from the event can be found here.

I managed to stock up on Betty’s tea whilst in York

A Crash Course in Health Analytics

As some of you might know, I recently made a (fairly large) career change. I’m now a Research Fellow in Health Data Analytics at The University of Leeds, UK. Since I’m coming from a maths/HPC background and have almost no prior knowledge of healthcare I’ve had a bit of catching up to do! Overall I’m aiming to apply machine learning and large-scale data analysis to large datasets arising from health and socio-economic domains, where my skills in linear algebra and HPC will undoubtedly become useful.

In this post I aim to summarise what I’ve learned in my first few weeks on the job. This is partly to archive things for myself but should also be interesting reading for anyone who wants to get involved with health data. I’ll touch upon

• the legal issues arising from using private data,
• interesting talks and papers that I’ve found, and,
• some recurring opinions on the future challenges in the field.

Batched BLAS Operations at SIAM CSE17

Over the last year, there has been significant interest in solving many small linear algebra problems simultaneously. Library vendors such as MKL and NVIDIA, along with researchers at instutions including Manchester, Tennessee, and Sandia National Labs have all been attempting to perform these calculations as efficiently as possible.

Over the weekend prior to the SIAM CSE17 meeting, many of those researchers (including myself) held a workshop to discuss strategies for batched BLAS (basic linear algebra subprogram) computations. Furthermore, lots of discussion was aimed at standardising the function APIs and the memory layout that users will interact with. The slides, and a number of research papers on the topic, are available at this page.

At the SIAM CSE17 meeting, our team at Manchester organised a minisymposium to discuss the highlights of our weekend with a wider audience. A brief summary of the four talks, along with a copy of their slides, is given below.

Linear Algebra in Sports Analytics

A piece I originally wrote for the Manchester SIAM Student Chapter blog.

Manchester SIAM-IMA Student Chapter Blog

Recently, due to the large amount of data available and the “Big data” buzz, there has been a surge of activity in applying maths to analyse sport. In addition to keeping tabs of the number of points scored and by whom, companies now collect player tracking data which can locate players to within a few centimetres multiple times per second! All of this new data opens many possibilities for interesting ways to analyse performance.

Sports analytics is growing fast in football.

Defensive Responsibility in Basketball

Measuring the defensive capability of players is a difficult problem. There are plenty of ways to assess offensive capability but, since defenders stop points being scored, it is harder to measure their effect on the game. With access to player tracking data from the NBA, Kirk Goldsberry has designed a model to see which defender is responsible for each attacker at any given time so that their defensive ability can be measured against the league average. Some more information on…

View original post 241 more words

SIAM ALA 15 – Minisymposium on Matrix Functions

Last week Nick Higham, Edvin Deadman, and I ran a minisymposium on matrix functions at the SIAM Applied Linear Algebra 2015 conference (link). This post gives a brief summary of each talk, links to published work, and (once they appear) links to the slides with synchronised audio.

Edit: Links to the talks are now available.

Attendance at the sessions was very good, with some high-quality questions coming from the audience.

The symposium had two sessions.

Session 1

• Marcel Schweitzer – Error Estimation in Krylov Subspace Methods for Matrix Functions
• Michele Benzi – Functions of Matrices with Kronecker Sum Structure
• Bruno Iannazzo – First-Order Riemannian Optimization Techniques for the Karcher Mean
• Sivan Toledo – A High Performance Algorithm for the Matrix Sign Function

Session 2

• Peter Kandolf – The Leja Method: Backward Error Analysis and Implementation
• Massimiliano Fasi – An Algorithm for the Lambert W Function on Matrices
• Antii Koskela – An Exponential Integrator for Polynomially Perturbed Linear ODEs
• Edvin Deadman – Estimating the condition number of f(A)b

Peter Kandolf describing the famour “hump” in the matrix exponential.

How to setup R using conda

Recently I’ve been working with some of the statistics staff at the University of Manchester on sports analytics. Specifically we’ve been looking for useful models in football data. People from this background normally use R to analyze data and fit models.

Normally I would use Python for this kind of task but, since there was already a considerable amount of code in R, it made sense for me to do some work in R. The people at Continuum Analytics (who make the brilliant Anaconda Python distribution) recently announced support for R using their package manager conda. However, it wasn’t easy to find instructions to get a fully working environment, so here is what I did.

What I Took Away from NACONF15, Glasgow

The Biennial Numerical Analysis Conference

This was the 26th Biennial Numerical Analysis Conference, marking 50 years since the conference series begun at the University of Saint Andrews in 1965. Some of the participants had been to (almost) every single one of the 26 conferences, whilst for other like myself it was their first time. The conference is renowned for the high quality of research presented, its friendly atmosphere, and the large range of topics presented.

How To Prepare For Your Viva

I’ve finally finished! After years of reading papers, designing algorithms, hacking at code, and writing papers, my PhD is complete.

One of the most daunting thoughts I had as a PhD student was the idea of the viva: two experts sit in a room and pick apart the fine details of your work. They ask deep and technical questions, not limited merely to your thesis content, for a few hours (I’ve heard horror stories of 8 hours!) before sending you out of the room to discuss your fate. Fifteen minutes of palpitations later you get your result and (whatever the outcome) head to the pub, either to celebrate or drown your sorrows as appropriate.

In reality, because I was well prepared, my viva was actually just a chat with some knowledgeable people who were very interested in my work. There were a few curveball questions, nothing too serious, and the whole thing was done in an hour.

Here are some of my top tips for viva preparation.

The finished product!

Modern Directions for Matrix Analysis and Applications

Every two years the IMA organize a conference on the interface between numerical linear algebra and optimization. For me, this was the perfect place to organize my first minisymposium entitled ‘Modern Directions for Matrix Analysis and Applications‘ with Natasa Strabic. We managed to get some great speakers talking about their ideas for future research. I’ve summarised some of their main ideas here and you can find my presentation on SlideShare.

Left to Right: Me, Amal Khabou, Ben Jeuris, Federico Poloni, Natasa Strabic, Roel Van Beeumen. Photo: Mario Berljafa.