{"id":47703,"date":"2024-03-27T12:57:05","date_gmt":"2024-03-27T16:57:05","guid":{"rendered":"https:\/\/engineering.jhu.edu\/ams\/?post_type=news&p=47703"},"modified":"2025-09-17T13:38:10","modified_gmt":"2025-09-17T17:38:10","slug":"making-ai-smarter-and-greener","status":"publish","type":"news","link":"https:\/\/engineering.jhu.edu\/ams\/news\/making-ai-smarter-and-greener\/","title":{"rendered":"Making AI Smarter and Greener\u00a0"},"content":{"rendered":"

Generative modeling allows computers that have been trained to recognize patterns and statistical probabilities in vast datasets to create images, audio, and videos. <\/span>But<\/span> generating this realistic-looking digital content requires a significant amount of computational power and resources, prompting researchers to explore avenues for efficiency without compromising quality.\u00a0<\/span>\u00a0<\/span><\/p>\n

A team that includes Johns Hopkins mathematician <\/span>Holden Lee<\/span><\/a> has developed a theoretical analysis aimed at making a form of generative modeling called diffusion modeling faster\u2014and less resource-heavy. The researchers presented <\/span>their results<\/span><\/a> at the NeurIPS conference in December.\u00a0<\/span>\u00a0<\/span><\/p>\n

“Diffusion models require immense computational resources, so practitioners use various tricks to speed them up. However, there\u2019s limited theoretical understanding of why they work. We gave the first proof that a class of such methods can result in substantial acceleration, requiring a sublinear number of steps for generation,\u201d said Lee, an assistant professor in the Department of Applied Mathematics and Statistics at the Whiting School of Engineering.<\/span>\u00a0<\/span><\/p>\n

The study compared two mathematical equations used in generative modeling: ordinary differential equations (ODE), which model smooth and continuous changes, and stochastic differential equations (SDE), which model \u201cnoisy,\u201d random changes, in terms of their behavior when simulated on a computer. They found that using ODEs for some computations in generative models could offer faster computational capabilities.\u00a0\u00a0<\/span>\u00a0<\/span><\/p>\n

“We wanted to unravel the mystery of why replacing SDEs with ODEs in these models improved efficiency. This was somewhat surprising because SDEs, which incorporate randomness, are a more natural choice for generating a data distribution, whereas ODEs are deterministic. So why did they do better than SDEs, which are designed to handle random noise?” Lee asked. \u201cWe aimed to develop a theory that explains this observed phenomenon.”\u00a0<\/span>\u00a0<\/span><\/p>\n

The researchers tackled this challenge by analyzing the number of steps required for the computer program to execute its task. They looked at the dependence on two important aspects: dimensionality (how many different parts or components the program needed to handle) and smoothness (how predictable those parts are).\u00a0\u00a0<\/span>\u00a0<\/span><\/p>\n

The team used a technique called a \u201ccoupling argument\u201d to compare the accuracy of their computer simulation, which was ODE-based, to an ideal process free from numerical or statistical error<\/span>.<\/span>. However, in contrast to the SDE simulation, the error from the ODE simulation was harder to control. They found a way to fix any mistakes or discrepancies that popped up during the simulation, using a “corrector” comprising a Markov chain Monte Carlo algorithm to make sure the simulation stayed close to the right track.\u00a0<\/span>\u00a0<\/span>\u00a0<\/span><\/p>\n

“Incorporating the corrector step is crucial for stability. For a high-quality generation, it’s advisable to utilize the corrector alongside the ODE,\u201d said Lee.\u00a0<\/span>\u00a0<\/span><\/p>\n

They found that by using this method, the computer program could do its job much more efficiently. The ODE-based algorithms speed up the process significantly, requiring fewer steps compared to the SDE-based approaches. However, this acceleration had a cost: the operation became more sensitive to unpredictable or \u201cnon-smooth\u201d elements in the data, sometimes increasing the number of steps needed and making errors harder to control.\u00a0\u00a0<\/span>\u00a0<\/span><\/p>\n

\u201cAs generative AI becomes increasingly ubiquitous, optimizing computational resources becomes imperative. By providing theoretical guarantees and practical guidance, our study lays a foundation for more efficient diffusion model implementations,\u201d Lee explains.<\/span>\u00a0<\/span><\/p>\n","protected":false},"template":"","class_list":["post-47703","news","type-news","status-publish","hentry","news_categories-applied-mathematics","news_categories-data-science","news_categories-research"],"acf":[],"yoast_head":"\nMaking AI Smarter and Greener\u00a0 | Department of Applied Mathematics and Statistics<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/engineering.jhu.edu\/ams\/news\/making-ai-smarter-and-greener\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Making AI Smarter and Greener\u00a0\" \/>\n<meta property=\"og:description\" content=\"Generative modeling allows computers that have been trained to recognize patterns and statistical probabilities in vast datasets to create images, audio, and videos. But generating this realistic-looking digital content requires…\" \/>\n<meta property=\"og:url\" content=\"https:\/\/engineering.jhu.edu\/ams\/news\/making-ai-smarter-and-greener\/\" \/>\n<meta property=\"og:site_name\" content=\"Department of Applied Mathematics and Statistics\" \/>\n<meta property=\"article:modified_time\" content=\"2025-09-17T17:38:10+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/engineering.jhu.edu\/ams\/wp-content\/uploads\/2024\/03\/shutterstock_1696920283-1024x576.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"1024\" \/>\n\t<meta property=\"og:image:height\" content=\"576\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/jpeg\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:title\" content=\"Making AI Smarter and Greener\u00a0\" \/>\n<meta name=\"twitter:image\" content=\"https:\/\/engineering.jhu.edu\/ams\/wp-content\/uploads\/2024\/03\/shutterstock_1696920283.jpg\" \/>\n<meta name=\"twitter:label1\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data1\" content=\"3 minutes\" \/>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Making AI Smarter and Greener\u00a0 | Department of Applied Mathematics and Statistics","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/engineering.jhu.edu\/ams\/news\/making-ai-smarter-and-greener\/","og_locale":"en_US","og_type":"article","og_title":"Making AI Smarter and Greener\u00a0","og_description":"Generative modeling allows computers that have been trained to recognize patterns and statistical probabilities in vast datasets to create images, audio, and videos. But generating this realistic-looking digital content requires…","og_url":"https:\/\/engineering.jhu.edu\/ams\/news\/making-ai-smarter-and-greener\/","og_site_name":"Department of Applied Mathematics and Statistics","article_modified_time":"2025-09-17T17:38:10+00:00","og_image":[{"width":1024,"height":576,"url":"https:\/\/engineering.jhu.edu\/ams\/wp-content\/uploads\/2024\/03\/shutterstock_1696920283-1024x576.jpg","type":"image\/jpeg"}],"twitter_card":"summary_large_image","twitter_title":"Making AI Smarter and Greener\u00a0","twitter_image":"https:\/\/engineering.jhu.edu\/ams\/wp-content\/uploads\/2024\/03\/shutterstock_1696920283.jpg","twitter_misc":{"Est. reading time":"3 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/engineering.jhu.edu\/ams\/news\/making-ai-smarter-and-greener\/","url":"https:\/\/engineering.jhu.edu\/ams\/news\/making-ai-smarter-and-greener\/","name":"Making AI Smarter and Greener\u00a0 | Department of Applied Mathematics and Statistics","isPartOf":{"@id":"https:\/\/engineering.jhu.edu\/ams\/#website"},"datePublished":"2024-03-27T16:57:05+00:00","dateModified":"2025-09-17T17:38:10+00:00","breadcrumb":{"@id":"https:\/\/engineering.jhu.edu\/ams\/news\/making-ai-smarter-and-greener\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/engineering.jhu.edu\/ams\/news\/making-ai-smarter-and-greener\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/engineering.jhu.edu\/ams\/news\/making-ai-smarter-and-greener\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/engineering.jhu.edu\/ams\/"},{"@type":"ListItem","position":2,"name":"News","item":"https:\/\/engineering.jhu.edu\/ams\/news\/"},{"@type":"ListItem","position":3,"name":"Making AI Smarter and Greener\u00a0"}]},{"@type":"WebSite","@id":"https:\/\/engineering.jhu.edu\/ams\/#website","url":"https:\/\/engineering.jhu.edu\/ams\/","name":"Hopkins Applied Math & Statistics","description":"Department of Applied Mathematics and Statistics","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/engineering.jhu.edu\/ams\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"}]}},"distributor_meta":false,"distributor_terms":false,"distributor_media":false,"distributor_original_site_name":"Department of Applied Mathematics and Statistics","distributor_original_site_url":"https:\/\/engineering.jhu.edu\/ams","push-errors":false,"_links":{"self":[{"href":"https:\/\/engineering.jhu.edu\/ams\/wp-json\/wp\/v2\/news\/47703","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/engineering.jhu.edu\/ams\/wp-json\/wp\/v2\/news"}],"about":[{"href":"https:\/\/engineering.jhu.edu\/ams\/wp-json\/wp\/v2\/types\/news"}],"wp:attachment":[{"href":"https:\/\/engineering.jhu.edu\/ams\/wp-json\/wp\/v2\/media?parent=47703"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}