Neural Ordinary Differential Equations

Neural ordinary differential equations Chen et al., NeurIPS’18 ‘Neural Ordinary Differential Equations’ won a best paper award at NeurIPS last month. It’s not an easy piece (at least not for me!), but in the spirit of ‘deliberate practice’ that doesn’t mean there isn’t something to be gained from trying to understand as much as possible. […]

Continue Reading

NVIDIA Sets Six Records in AI Performance

NVIDIA has set six AI performance records with today’s release of the industry’s first broad set of AI benchmarks. Backed by Google, Intel, Baidu, NVIDIA and dozens more technology leaders, the new MLPerf benchmark suite measures a wide range of deep learning workloads. Aiming to serve as the industry’s first objective AI benchmark suite, it […]

Continue Reading

GraphIt: A high-performance graph DSL

GraphIt: a high-performance graph DSL Zhang et al., OOPSLA’18 See also: http://graphit-lang.org/. The problem with finding the optimal algorithm and data structures for a given problem is that so often it depends. This is especially true when it comes to graph algorithms. It is difficult to implement high-performance graph algorithms. The performance bottlenecks of these […]

Continue Reading

FairSwap: how to fairly exchange digital goods

FairSwap: how to fairly exchange digital goods Dziembowski et al., CCS’18 (Preprint) This is a transactions paper with a twist. The transactions we’re talking about are purchases of digital assets. More specifically, the purchase of a file (document, movie, archive of a dataset, …). The property we strongly care about is atomicity: either the seller […]

Continue Reading