Posts on argmax(blog)

Posts on argmax(blog) https://argmax.blog/posts/ Recent content in Posts on argmax(blog) argmax(blog) https://argmax.blog/%3Clink%20or%20path%20of%20image%20for%20opengraph,%20twitter-cards%3E https://argmax.blog/%3Clink%20or%20path%20of%20image%20for%20opengraph,%20twitter-cards%3E Hugo -- gohugo.io en-us Fri, 19 Sep 2025 00:00:00 +0000 A quantitative measure of mode-seeking vs. mode-covering preferences https://argmax.blog/posts/modes-psi-tradeoff/ Fri, 19 Sep 2025 00:00:00 +0000 https://argmax.blog/posts/modes-psi-tradeoff/ Another view Stein discrepancy is mode-seeking https://argmax.blog/posts/modes-stein/ Thu, 18 Sep 2025 00:00:00 +0000 https://argmax.blog/posts/modes-stein/ Stein discrepancy is more mode-seeking than reverse KL Sampler evaluation: No mode-covering without importance sampling https://argmax.blog/posts/modes-coverage-or-is/ Wed, 17 Sep 2025 00:00:00 +0000 https://argmax.blog/posts/modes-coverage-or-is/ An impossibility result Defining mode-covering behavior with gradient analysis https://argmax.blog/posts/modes-cover-definition/ Tue, 16 Sep 2025 00:00:00 +0000 https://argmax.blog/posts/modes-cover-definition/ What does mode-seeking vs. mode-covering behavior in distributional divergences really mean? Outranking leaderboard models on test sets, with only their predictions https://argmax.blog/posts/leaderboard-attack/ Tue, 21 Jan 2025 00:00:00 +0000 https://argmax.blog/posts/leaderboard-attack/ A brainteaser On diversity and many-model ensembling: AI government & AI-augmented public goods funding https://argmax.blog/posts/deepfunding-01/ Tue, 14 Jan 2025 00:00:00 +0000 https://argmax.blog/posts/deepfunding-01/ When AI agents outnumber voters, how should we elect an AI government? The deep retrieval + remixing hypothesis https://argmax.blog/posts/deep-retrieval-remix-hypothesis/ Thu, 28 Mar 2024 00:00:00 +0000 https://argmax.blog/posts/deep-retrieval-remix-hypothesis/ How do modern deep generative models produce high-quality outputs? What is data? The classical and postmodern views https://argmax.blog/posts/data-two-views/ Wed, 27 Mar 2024 00:00:00 +0000 https://argmax.blog/posts/data-two-views/ Is data sacred? On Creating AGI within Capitalism -- The Greatest Threat to AGI is ANI. https://argmax.blog/posts/agi-capitalism/ Fri, 30 Sep 2022 00:00:00 +0000 https://argmax.blog/posts/agi-capitalism/ A speculative argument Implicit regularization of SGD in a linear model https://argmax.blog/posts/implicit-reg-sgd-linear/ Wed, 28 Sep 2022 00:00:00 +0000 https://argmax.blog/posts/implicit-reg-sgd-linear/ A brief mathematical result Treating high-dimensional prediction/generation as optimization https://argmax.blog/posts/prediction-as-optimization/ Mon, 29 Aug 2022 00:00:00 +0000 https://argmax.blog/posts/prediction-as-optimization/ Exploring connections between diffusion models, alphafold's recycling, structured prediction energy networks, and manifold learning. Primer on Score-based Generative Models https://argmax.blog/posts/primer-score-based/ Sun, 14 Aug 2022 00:00:00 +0000 https://argmax.blog/posts/primer-score-based/ An introduction Implicit Differentiation through Equilibria https://argmax.blog/posts/implicit-differentiation/ Wed, 20 Jul 2022 00:00:00 +0000 https://argmax.blog/posts/implicit-differentiation/ An introduction. On KL Divergence in Discrete Spaces https://argmax.blog/posts/kl-discrete/ Tue, 12 Jul 2022 00:00:00 +0000 https://argmax.blog/posts/kl-discrete/ KL behaves differently in discrete spaces than in continuous spaces.