View this talk on talks.cam (opens in new tab)<\/span><\/a>Opens in a new tab<\/span><\/p>\n Frontiers in Artificial Intelligence is a series of public lectures at Microsoft Research Cambridge featuring leading researchers in the field, focusing on the cutting edge topics at the intersection of machine learning, statistics, and artificial intelligence. Students, scientists, and engineers in academia and industry are all welcome to join us for these exciting talks and the opportunity to socialize with the Cambridge AI\/ML community.<\/p>\n Deep learning methods achieve state-of-the-art performance in many application scenarios. Yet, these methods require a significant amount of hyperparameters tuning in order to achieve the best results. In particular, tuning the learning rates in the stochastic optimization process is still one of the main bottlenecks.<\/p>\n In this talk, I will propose a new stochastic gradient descent procedure that does not require any learning rate setting. Contrary to previous methods, we do not adapt the learning rates nor we make use of the assumed curvature of the objective function. Instead, we reduce the optimization process to a game of betting on a non-stochastic coin and we propose an optimal strategy based on a generalization of Kelly betting. Moreover, I’ll show how this reduction can be also used for other machine learning problems.<\/p>\n Theoretical convergence is proven for convex and quasi-convex functions and empirical evidence shows the advantage of our algorithm over popular stochastic gradient algorithms<\/p>\n Opens in a new tab<\/span><\/p>\n Regina Barzilay – How Can NLP Help Cure Cancer? (opens in new tab)<\/span><\/a><\/p>\n Aapo Hyvarinen – Nonlinear ICA using temporal structure: a principled framework for unsupervised deep learning\u00a0<\/a><\/p>\n Max Welling – Generalizing Convolutions for Deep Learning <\/a>Opens in a new tab<\/span><\/p>\n","protected":false},"excerpt":{"rendered":" 21 Station Road Cambridge CB1 2FB View the whole series on talks.cam (opens in new tab) View this talk on talks.cam (opens in new tab)Opens in a new tab Frontiers in Artificial Intelligence is a series of public lectures at Microsoft Research Cambridge featuring leading researchers in the field, focusing on the cutting edge topics […]<\/p>\n","protected":false},"featured_media":0,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"_classifai_error":"","msr_startdate":"2017-08-24","msr_enddate":"2017-08-24","msr_location":"Microsoft Research Cambridge UK","msr_expirationdate":"","msr_event_recording_link":"","msr_event_link":"","msr_event_link_redirect":false,"msr_event_time":"13:00","msr_hide_region":true,"msr_private_event":false,"msr_hide_image_in_river":0,"footnotes":""},"research-area":[13556],"msr-region":[239178],"msr-event-type":[197944],"msr-video-type":[],"msr-locale":[268875],"msr-program-audience":[],"msr-post-option":[],"msr-impact-theme":[],"class_list":["post-400724","msr-event","type-msr-event","status-publish","hentry","msr-research-area-artificial-intelligence","msr-region-europe","msr-event-type-hosted-by-microsoft","msr-locale-en_us"],"msr_about":"\n\n 21 Station Road View the whole series on talks.cam (opens in new tab)<\/span><\/a><\/p>\n View this talk on talks.cam (opens in new tab)<\/span><\/a>Opens in a new tab<\/span><\/p>\n Frontiers in Artificial Intelligence is a series of public lectures at Microsoft Research Cambridge featuring leading researchers in the field, focusing on the cutting edge topics at the intersection of machine learning, statistics, and artificial intelligence. Students, scientists, and engineers in academia and industry are all welcome to join us for these exciting talks and the opportunity to socialize with the Cambridge AI\/ML community.<\/p>\n Deep learning methods achieve state-of-the-art performance in many application scenarios. Yet, these methods require a significant amount of hyperparameters tuning in order to achieve the best results. In particular, tuning the learning rates in the stochastic optimization process is still one of the main bottlenecks.<\/p>\n In this talk, I will propose a new stochastic gradient descent procedure that does not require any learning rate setting. Contrary to previous methods, we do not adapt the learning rates nor we make use of the assumed curvature of the objective function. Instead, we reduce the optimization process to a game of betting on a non-stochastic coin and we propose an optimal strategy based on a generalization of Kelly betting. Moreover, I’ll show how this reduction can be also used for other machine learning problems.<\/p>\n Theoretical convergence is proven for convex and quasi-convex functions and empirical evidence shows the advantage of our algorithm over popular stochastic gradient algorithms<\/p>\n Opens in a new tab<\/span><\/p>\n Regina Barzilay – How Can NLP Help Cure Cancer?<\/a><\/p>\n Aapo Hyvarinen – Nonlinear ICA using temporal structure: a principled framework for unsupervised deep learning\u00a0<\/a><\/p>\n Max Welling – Generalizing Convolutions for Deep Learning <\/a>Opens in a new tab<\/span><\/p>\n","tab-content":[{"id":0,"name":"About","content":"Frontiers in Artificial Intelligence is a series of public lectures at Microsoft Research Cambridge featuring leading researchers in the field, focusing on the cutting edge topics at the intersection of machine learning, statistics, and artificial intelligence. Students, scientists, and engineers in academia and industry are all welcome to join us for these exciting talks and the opportunity to socialize with the Cambridge AI\/ML community.\r\n<\/h3>\n
![\"\"](\"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-content\/uploads\/2017\/07\/photo_color-1-211x300.png\")
Coin Betting for Backprop without Learning Rates and More<\/h3>\nDr\u00a0Francesco Orabona, Stony Brook University<\/h4>\n
\nCambridge
\nCB1 2FB<\/p>\n<\/h3>\n
Coin Betting for Backprop without Learning Rates and More<\/h3>\nDr\u00a0Francesco Orabona, Stony Brook University<\/h4>\n
<\/h3>\r\n
Coin Betting for Backprop without Learning Rates and More<\/h3>\r\nDr\u00a0Francesco Orabona, Stony Brook University<\/h4>\r\nDeep learning methods achieve state-of-the-art performance in many application scenarios. Yet, these methods require a significant amount of hyperparameters tuning in order to achieve the best results. In particular, tuning the learning rates in the stochastic optimization process is still one of the main bottlenecks.\r\n\r\nIn this talk, I will propose a new stochastic gradient descent procedure that does not require any learning rate setting. Contrary to previous methods, we do not adapt the learning rates nor we make use of the assumed curvature of the objective function. Instead, we reduce the optimization process to a game of betting on a non-stochastic coin and we propose an optimal strategy based on a generalization of Kelly betting. Moreover, I'll show how this reduction can be also used for other machine learning problems.\r\n\r\nTheoretical convergence is proven for convex and quasi-convex functions and empirical evidence shows the advantage of our algorithm over popular stochastic gradient algorithms\r\n\r\n "},{"id":1,"name":"Past Speakers","content":"Regina Barzilay - How Can NLP Help Cure Cancer?<\/a>\r\n\r\nAapo Hyvarinen - Nonlinear ICA using temporal structure: a principled framework for unsupervised deep learning\u00a0<\/a>\r\n\r\nMax Welling - Generalizing Convolutions for Deep Learning <\/a>"}],"msr_startdate":"2017-08-24","msr_enddate":"2017-08-24","msr_event_time":"13:00","msr_location":"Microsoft Research Cambridge UK","msr_event_link":"","msr_event_recording_link":"","msr_startdate_formatted":"August 24, 2017","msr_register_text":"Watch now","msr_cta_link":"","msr_cta_text":"","msr_cta_bi_name":"","featured_image_thumbnail":null,"event_excerpt":"Frontiers in Artificial Intelligence is a series of public lectures at Microsoft Research Cambridge featuring leading researchers in the field, focusing on the cutting edge topics at the intersection of machine learning, statistics, and artificial intelligence. Students, scientists, and engineers in academia and industry are all welcome to join us for these exciting talks and the opportunity to socialize with the Cambridge AI\/ML community. Coin Betting for Backprop without Learning Rates and More Dr\u00a0Francesco Orabona,…","msr_research_lab":[199561],"related-researchers":[],"msr_impact_theme":[],"related-academic-programs":[],"related-groups":[],"related-projects":[],"related-opportunities":[],"related-publications":[],"related-videos":[],"related-posts":[],"_links":{"self":[{"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-event\/400724","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-event"}],"about":[{"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-event"}],"version-history":[{"count":2,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-event\/400724\/revisions"}],"predecessor-version":[{"id":1147156,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-event\/400724\/revisions\/1147156"}],"wp:attachment":[{"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/media?parent=400724"}],"wp:term":[{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=400724"},{"taxonomy":"msr-region","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-region?post=400724"},{"taxonomy":"msr-event-type","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-event-type?post=400724"},{"taxonomy":"msr-video-type","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-video-type?post=400724"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=400724"},{"taxonomy":"msr-program-audience","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-program-audience?post=400724"},{"taxonomy":"msr-post-option","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-post-option?post=400724"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=400724"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}