Zoom link: https://upenn.zoom.us/j/98220304722 Abstract I will present recent work by my research group on the design and analysis of stochastic-gradient-based algorithms for solving nonconvex constrained optimization problems, which may arise, for example, in informed supervised learning. I will focus in particular on algorithmic strategies that have consistently been shown to exhibit the best practical […]
Colloquium
Calendar of Events
S
Sun
|
M
Mon
|
T
Tue
|
W
Wed
|
T
Thu
|
F
Fri
|
S
Sat
|
---|---|---|---|---|---|---|
0 events,
|
0 events,
|
0 events,
|
0 events,
|
1 event,
-
|
0 events,
|
0 events,
|
0 events,
|
0 events,
|
0 events,
|
0 events,
|
1 event,
-
We present a new perspective on online learning that we refer to as gradient equilibrium: a sequence of iterates achieves gradient equilibrium if the average of gradients of losses along the sequence converges to zero. In general, this condition is not implied by, nor implies, sublinear regret. It turns out that gradient equilibrium is achievable […] |
1 event,
-
Polymers are ubiquitous in both synthetic and biological materials and underlie technologies as diverse as surfactants, adhesives, proteins and DNA. One of the defining features of all polymeric materials is that they are characterized by a wide range of length scales, often involving phenomena that span nanometers to microns. This hierarchy of length scales presents […] |
0 events,
|
0 events,
|
0 events,
|
0 events,
|
0 events,
|
1 event,
-
Zoom link: https://upenn.zoom.us/j/98220304722 Abstract: This talk considers the problem of resilient distributed multi-agent optimization for cyberphysical systems in the presence of malicious or non-cooperative agents. It is assumed that stochastic values of trust between agents are available which allows agents to learn their trustworthy neighbors simultaneously with performing updates to minimize their own local […] |
0 events,
|
0 events,
|
0 events,
|
1 event,
-
In this guest lecture, we will cover two recent research thrusts from the RobotiXX lab in taking RoboRacer off-road: high-speed off-road navigation and wheeled mobility on vertically challenging terrain. For high-speed off-road navigation, we will introduce a sequential line of work with every work inspired by and built upon its prior work, ranging from inverse […] |
0 events,
|
1 event,
-
The compute demands of AI and robotics continue to rise due to the rapidly growing volume of data to be processed; the increasingly complex algorithms for higher quality of results; and the demands for energy efficiency and real-time performance. In this talk, we will discuss the design of efficient tailored hardware accelerators and the co-design […] |
1 event,
-
Zoom link: https://upenn.zoom.us/j/98220304722 Abstract: Solving min-max problems is a central question in optimization, games, learning, and controls. Arguably the most natural algorithm is Gradient-Descent-Ascent (GDA), however since the 1970s, conventional wisdom has argued that it fails to converge even on simple problems. This failure spurred the extensive literature on modifying GDA with extragradients, optimism, momentum, anchoring, […] |
0 events,
|
0 events,
|
0 events,
|
0 events,
|
0 events,
|
0 events,
|
0 events,
|
1 event,
-
In this talk, I will discuss recent publications from my group that attempt at learning models of the world and the effect of the actions of an agent within that world self-supervised, solely via interaction. In particular, I will discuss the potential and challenges of video generative models as a candidate for such a world […] |
0 events,
|