Can kernel machines be a viable alternative to deep neural networks?

Add to your list(s) Download to your calendar using vCal

• Dr Parthe Pandit, Indian Institute of Technology, Bombay
• Tuesday 25 February 2025, 14:00-15:00
• JDB Seminar Room, CUED.

If you have a question about this talk, please contact Prof. Ramji Venkataramanan.

Deep learning remains an art with several heuristics that do not always translate across application domains. Kernel machines, a classical model in ML, have received renewed attention following the discovery of the Neural Tangent Kernel and its equivalence to wide neural networks. I will present 2 results which show the promise of kernel machines for modern large scale applications. 1. Data-dependent supervised kernels: https://www.science.org/stoken/author-tokens/ST-1738/full 2. Fast scalable training algorithms for kernel machines: https://arxiv.org/abs/2411.16658

Bio: Parthe Pandit is the Thakur Family Chair Assistant Professor at the Center for Machine Intelligence and Data Science at IIT Bombay. He was a Simons Postdoctoral Fellow at UC San Diego. He obtained his PhD from UCLA and his undergraduate education from IIT Bombay. In 2024, he was awarded the AI2050 Early Career Fellowship by Schmidt Sciences. He has also been the recipient of the 2019 Jack K Wolf Student paper award by the IEEE Information Theory Society.

This talk is part of the Signal Processing and Communications Lab Seminars series.

This talk is included in these lists:

• All Talks (aka the CURE list)
• Cambridge Centre for Data-Driven Discovery (C2D3)
• Cambridge University Engineering Department Talks
• Cambridge talks
• Centre for Smart Infrastructure & Construction
• Chris Davis' list
• Computational Continuum Mechanics Group Seminars
• Featured lists
• Information Engineering Division seminar list
• Interested Talks
• JDB Seminar Room, CUED
• School of Technology
• Signal Processing and Communications Lab Seminars
• Trust & Technology Initiative - interesting events
• bld31
• ndk22's list
• ob366-ai4er
• rp587

Note that ex-directory lists are not shown.