Matches in SemOpenAlex for { <https://semopenalex.org/work/W1496132382> ?p ?o ?g. }
- W1496132382 abstract "In the last several years, the intimate connection between convex optimization and learning problems, in both statistical and sequential frameworks, has shifted the focus of algorithmic machine learning to examine this interplay. In particular, on one hand, this intertwinement brings forward new challenges in reassessment of the performance of learning algorithms including generalization and regret bounds under the assumptions imposed by convexity such as analytical properties of loss functions (e.g., Lipschitzness, strong convexity, and smoothness). On the other hand, emergence of datasets of an unprecedented size, demands the development of novel and more efficient optimization algorithms to tackle large-scale learning problems. The overarching goal of this thesis is to reassess the smoothness of loss functions in statistical learning, sequential prediction/online learning, and stochastic optimization and explicate its consequences. In particular we examine how smoothness of loss function could be beneficial or detrimental in these settings in terms of sample complexity, statistical consistency, regret analysis, and convergence rate, and investigate how smoothness can be leveraged to devise more efficient learning algorithms." @default.
- W1496132382 created "2016-06-24" @default.
- W1496132382 creator A5076083402 @default.
- W1496132382 date "2014-07-19" @default.
- W1496132382 modified "2023-09-27" @default.
- W1496132382 title "Exploiting Smoothness in Statistical Learning, Sequential Prediction, and Stochastic Optimization" @default.
- W1496132382 cites W1464850230 @default.
- W1496132382 cites W146740654 @default.
- W1496132382 cites W1483788985 @default.
- W1496132382 cites W1485418074 @default.
- W1496132382 cites W1488797257 @default.
- W1496132382 cites W1501884374 @default.
- W1496132382 cites W1505731132 @default.
- W1496132382 cites W1508384000 @default.
- W1496132382 cites W1509803206 @default.
- W1496132382 cites W1516903196 @default.
- W1496132382 cites W1519060350 @default.
- W1496132382 cites W1520045492 @default.
- W1496132382 cites W153281708 @default.
- W1496132382 cites W1542886316 @default.
- W1496132382 cites W1545471058 @default.
- W1496132382 cites W1547176662 @default.
- W1496132382 cites W1552828154 @default.
- W1496132382 cites W1556545893 @default.
- W1496132382 cites W1566207273 @default.
- W1496132382 cites W1570963478 @default.
- W1496132382 cites W1574851760 @default.
- W1496132382 cites W1583497301 @default.
- W1496132382 cites W1615597061 @default.
- W1496132382 cites W1775587472 @default.
- W1496132382 cites W178986290 @default.
- W1496132382 cites W1790582767 @default.
- W1496132382 cites W180686687 @default.
- W1496132382 cites W1939652453 @default.
- W1496132382 cites W1964009380 @default.
- W1496132382 cites W1978259121 @default.
- W1496132382 cites W1979675141 @default.
- W1496132382 cites W1982032418 @default.
- W1496132382 cites W1982381767 @default.
- W1496132382 cites W1982813377 @default.
- W1496132382 cites W1988790447 @default.
- W1496132382 cites W1989274820 @default.
- W1496132382 cites W1992208280 @default.
- W1496132382 cites W1999678910 @default.
- W1496132382 cites W2000955051 @default.
- W1496132382 cites W2004001705 @default.
- W1496132382 cites W2011395874 @default.
- W1496132382 cites W2014384147 @default.
- W1496132382 cites W2014482607 @default.
- W1496132382 cites W2019363670 @default.
- W1496132382 cites W2022465039 @default.
- W1496132382 cites W2023163512 @default.
- W1496132382 cites W2024046085 @default.
- W1496132382 cites W2024484010 @default.
- W1496132382 cites W2029538739 @default.
- W1496132382 cites W2029604420 @default.
- W1496132382 cites W2030161963 @default.
- W1496132382 cites W2041615247 @default.
- W1496132382 cites W2044293264 @default.
- W1496132382 cites W2045313701 @default.
- W1496132382 cites W2045744861 @default.
- W1496132382 cites W2049393399 @default.
- W1496132382 cites W2051922388 @default.
- W1496132382 cites W2056003475 @default.
- W1496132382 cites W2068221105 @default.
- W1496132382 cites W2068643490 @default.
- W1496132382 cites W2069317438 @default.
- W1496132382 cites W2076605490 @default.
- W1496132382 cites W2077008409 @default.
- W1496132382 cites W2077723394 @default.
- W1496132382 cites W2083459869 @default.
- W1496132382 cites W2087258353 @default.
- W1496132382 cites W2088253680 @default.
- W1496132382 cites W2089559088 @default.
- W1496132382 cites W2093825590 @default.
- W1496132382 cites W2095762034 @default.
- W1496132382 cites W2096840748 @default.
- W1496132382 cites W2098158197 @default.
- W1496132382 cites W2098741260 @default.
- W1496132382 cites W2100483895 @default.
- W1496132382 cites W2105875671 @default.
- W1496132382 cites W2106458073 @default.
- W1496132382 cites W2106887613 @default.
- W1496132382 cites W2108948681 @default.
- W1496132382 cites W2109339818 @default.
- W1496132382 cites W2109445534 @default.
- W1496132382 cites W2109706083 @default.
- W1496132382 cites W2110654099 @default.
- W1496132382 cites W2110947625 @default.
- W1496132382 cites W2112269233 @default.
- W1496132382 cites W2112531253 @default.
- W1496132382 cites W2113651538 @default.
- W1496132382 cites W2114609025 @default.
- W1496132382 cites W2115807064 @default.
- W1496132382 cites W2119821739 @default.
- W1496132382 cites W2120745256 @default.
- W1496132382 cites W2121367301 @default.
- W1496132382 cites W2122299160 @default.
- W1496132382 cites W2124488712 @default.
- W1496132382 cites W2129113961 @default.