ESE Fall Seminar – “Acceleration by Stepsize Hedging”

Glandt Forum, Singh Center for Nanotechnology 3205 Walnut Street, Philadelphia, PA, United States

Can we accelerate convergence of gradient descent without changing the algorithm --- just by optimizing stepsizes? Surprisingly, we show that the answer is yes. Our proposed Silver Stepsize Schedule optimizes […]

ESE Fall Seminar – “Quantum sensing and imaging with diamond spins”

Berger Auditorium (Room 13), Skirkanich Hall 210 South 33rd Street, Philadelphia, PA, United States

Solid state spin qubits, in particular the nitrogen vacancy (NV) center in diamond, offer a path towards truly nanoscale imaging of condensed matter and biological systems with sensitivity to single […]

ESE Fall Seminar – “Approximate symmetries in machine learning”

Glandt Forum, Singh Center for Nanotechnology 3205 Walnut Street, Philadelphia, PA, United States

In this talk, we explain different roles that symmetries and approximate symmetries can play in machine learning models. We define approximately equivariant graph neural networks and we show a bias-variance […]

ESE Fall Seminar – “Stochastic Geometry for Networks”

Berger Auditorium (Room 13), Skirkanich Hall 210 South 33rd Street, Philadelphia, PA, United States

Stochastic geometry is a branch of probability theory that deals with the study of random spatial patterns. Random point patterns, termed point processes, are the most basic such objects that […]