http://www.cs.ox.ac.uk/seminars/ en-gb 360 Wed, 04 Nov 2026 10:26:18 GMT Wed, 04 Nov 2026 10:26:18 GMT Distribution Matching Evolutionary Algorithms for Discovery http://blogs.law.harvard.edu/tech/rss/ http://www.cs.ox.ac.uk/seminars/2864.html <p class="xmsonormal"><span style="color: black;">A novel discovery is one which is both useful and surprising. For generative models, an output is useful if it has a high reward and is surprising if it has a low probability. In this talk I will detail a method for sampling high reward low probability outputs from generative models, outputs which we would colloquially call novel discoveries. This method is based on a framework interpreting evolutionary algorithms as implementing approximate probabilistic inference. I will conclude by sharing some potential extensions of this framework which would enable developing other, perhaps more performant, algorithms for discovery.</span></p> <p class="xmsonormal"><em><span style="color: black;">Bio: Yonatan is a DPhil student at Oxford working on probabilistic AI methods for automated discovery, with a special focus on developing principled evolutionary algorithms. Previously, Yonatan obtained his master&rsquo;s in computer science from the University of Cambridge and worked on maps for autonomous vehicles at Mobileye. His PhD is funded by the AIMS CDT and a Rhodes scholarship.</span></em></p> <p class="xmsonormal"><strong><span style="color: black;">You can also j</span><span style="color: black;">oin online: </span><a href="https://meet.google.com/vgs-cctr-esu">https://meet.google.com/vgs-cctr-esu</a></strong></p> <br/>Room 051, Wolfson Building Distribution Matching Evolutionary Algorithms for Discovery oucl-seminar-Distribution Matching Evolutionary Algorithms for Discovery-2864 Wed, 04 Nov 2026 10:26:18 GMT