video thumbnail
Pause
Mute
Subtitles
Playback speed
0.25
0.5
0.75
1
1.25
1.5
1.75
2
Full screen

On the Complexity of Bandit and Derivative-Free Stochastic Convex Optimization

Published on Feb 4, 20252806 Views

The problem of stochastic convex optimization with bandit feedback (in the learning community) or without knowledge of gradients (in the optimization community) has received much attention in recent y

Related categories

Presentation

On the Complexity of Bandit and Derivative-Free Stochastic Convex Optimization00:00
Bandit / Derivative-Free Stochastic Convex Optimization (1)00:00
Bandit / Derivative-Free Stochastic Convex Optimization (2)00:29
Attainable Performance (1)02:01
Attainable Performance (2)02:47
Attainable Performance (3)02:51
Attainable Performance (4)03:07
Attainable Performance (5)03:30
Our Results (1)04:16
Our Results (2)04:41
Our Results (3)05:02
Our Results (4)05:57
Our Results (5)06:35
Quadratic Functions: Upper Bounds (1)06:53
Quadratic Functions: Upper Bounds (2)07:41
Quadratic Functions: Upper Bounds (3)10:25
Quadratic Functions: Upper Bounds (4)11:19
Quadratic Functions: Lower Bounds (1)12:02
Proof Idea12:29
Quadratic Functions: Lower Bounds (2)13:08
Strongly Convex and Smooth Functions15:10
Summary16:26