May 6, 2015

Anglican the Probabilistic Programming Concept

Filed under: Computer Science, Machine Learning — dvd @ 1:44 am

Anglican is a probabilistic programming language, or better yet, a concept, living in symbiosis with Clojure. Anglican stands for Church of England (because we are here in Oxford). To create your Turing-complete probabilistic models, clone anglican-user and hack away. Or, look at cool examples.

Read more…

Old Job Talk Slides

Filed under: Artificial Intelligence, Computer Science — Tags: — dvd @ 1:27 am

Found my own slides from a talk I gave a year ago, about rational meta-reasoning. Do they seem interesting to me because I have degraded during this year?

December 10, 2014

Output-Sensitive Adaptive MH for Probabilistic Programs

Filed under: Machine Learning — dvd @ 12:20 pm

A poster for the 3rd NIPS Workshop on Probabilistic Programming; also available as A0 PDF. Slides for a 15-minute talk.



November 19, 2014

Merge-and-Restart Meta-Agent Conflict-Based Search
for Multi-agent Path Finding

Filed under: Artificial Intelligence, Computer Science, Search, Uncategorized — Tags: , , , — dvd @ 6:48 pm

We introduce a new algorithm for multi-agent path finding, derived from the idea of meta-agent conflict-based search (MA-CBS). MA-CBS is a recently proposed algorithm for the multi-agent path finding problem. The algorithm is an extension of Conflict-Based Search (CBS), which automatically merges conflicting agents into meta-agents if the number of conflicts exceeds a certain threshold. However, the decision to merge agents is made according to an empirically chosen fixed threshold on the number of conflicts. The best threshold depends both on the domain and on the number of agents, and the nature of the dependence is not clearly understood.

We suggest a justification for the use of a fixed threshold on the number of conflicts based on the analysis of a model problem. Following the suggested justification, we introduce a new algorithm, which differs in the ways when and how meta-agents are created and handled during search. The new algorithm exhibits considerably better performance compared to the original algorithm. The new algorithm is evaluated on several sets of problems, chosen to highlight different aspects of the algorithm.

Full PDF

This is a short version of Justifying and Improving MA-CBS.

October 2, 2014

Slides for my Tea Talk

Filed under: Uncategorized — dvd @ 12:55 am

My Tea Talk slides, on October 1st, 2014.

October 8, 2013


Filed under: Artificial Intelligence, Computer Science, Uncategorized — Tags: — dvd @ 2:07 am

My dissertation “Rational Metareasoning in Problem-Solving Search”.

August 22, 2012

VOI-aware MCTS

Filed under: Uncategorized — dvd @ 10:01 am

A poster for the paper VOI-aware MCTS to appear at ECAI 2012. The paper is a short version of the second part of Selecting Computations: Theory and Application (UAI 2012).



July 24, 2012

AAAI 2012 Paper: MCTS based on Simple Regret

Filed under: Artificial Intelligence, Computer Science — dvd @ 12:01 am

Another poster in S5/HTML.

May 30, 2011

Poster for IJCAI-2011

Filed under: Computer Science — dvd @ 4:37 pm

I am having the pleasure of preparing a poster for IJCAI 2011, for the first time in my life. Both the IJCAI and a poster. Fiddling with PowerPoint or Illustrator is painful. Beautiful slides can be prepared with S5 using HTML and CSS; a poster in HTML and CSS is also worth a try.

Here is my HTML and CSS conference poster. Topics zoom in and out when you click on them. A PDF version for printing is also two clicks away in a decent web browser (that is, Mozilla Firefox).

I am less fearful of preparing conference posters now.

April 5, 2011

Modern archaic digital typography

Filed under: Computer Science — dvd @ 12:29 am

Modern scientific digital typography got stuck in a local maximum. LATEX — an archaic idiosyncratical tool — does everything wrong, even hyphenation and paragraph formatting. But this wrongdoing is so polished that cannot be improved. There will be no better LATEX until the ugly fashion for frozen fossils of scientific mind will pass away, and there will be no LATEX at all.

Hopefully soon.

Older Posts »

Powered by WordPress