A Marie Curie Fellow from Inria and UIUC presented research on stochastic gradient descent (SGD) through the lens of Markov processes, exploring the relationships between heavy-tailed distributions, generalization error, and algorithmic stability. The research challenges existing theories about the monotonic relationship between heavy tails and generalization error. It introduces a unified approach for proving Wasserstein stability bounds in stochastic optimization, applicable to convex and non-convex losses. Why it matters: The work provides novel insights into the theoretical underpinnings of stochastic optimization, relevant to researchers at MBZUAI and other institutions in the region working on machine learning algorithms.
KAUST Professor Peter Richtárik received a Distinguished Speaker Award at the Sixth International Conference on Continuous Optimization (ICCOPT 2019) in Berlin. Richtárik's lecture series, totaling six hours, focused on stochastic gradient descent (SGD) methods, drawing from recent research by his KAUST group. He highlighted key principles and new variants of SGD, the key method for training modern machine learning models. Why it matters: This award recognizes KAUST's contribution to fundamental machine learning optimization, which is critical for advancing AI in the region.
A delegation of senior officials from Singapore, including Minister Mohamed Maliki Bin Osman and Ambassador Kamal R. Vaswani, visited MBZUAI. They were hosted by MBZUAI's VP of Corporate Services Ian Matthews, Director of Outreach and Engagement Dr. Hosni Ghedira, and Director of Special Projects, Yun Xu. The visit involved discussions about MBZUAI's achievements and potential future collaborations. Why it matters: This signals growing international interest in MBZUAI and opportunities for partnerships in AI research and education between the UAE and Singapore.
Mladen Kolar from the University of Chicago Booth School of Business discussed stochastic optimization with equality constraints at MBZUAI. He presented a stochastic algorithm based on sequential quadratic programming (SQP) using a differentiable exact augmented Lagrangian. The algorithm adapts random stepsizes using a stochastic line search procedure, establishing global "almost sure" convergence. Why it matters: The presentation highlights MBZUAI's role in hosting discussions on advanced optimization techniques, fostering research and knowledge exchange in the field of machine learning.
A delegation from Singapore, led by Ambassador Kamal R Vaswani, visited Mohamed bin Zayed University of Artificial Intelligence (MBZUAI) in Abu Dhabi. The delegation toured the campus and learned about MBZUAI's AI vision. Discussions included the UAE's AI ecosystem and potential future collaborations between Singapore and MBZUAI. Why it matters: Fostering international partnerships between institutions like MBZUAI and Singapore can accelerate AI research and development in the region.
Alexander Gasnikov from the Moscow Institute of Physics and Technology presented a talk on open problems in convex optimization. The talk covered stochastic averaging vs stochastic average approximation, saddle-point problems and accelerated methods, homogeneous federated learning, and decentralized optimization. Gasnikov's research focuses on optimization algorithms and he has published in NeurIPS, ICML, EJOR, OMS, and JOTA. Why it matters: While the talk itself isn't directly related to GCC AI, understanding convex optimization is crucial for advancing machine learning algorithms used in the region.
The Saudi Data and Artificial Intelligence Authority (SDAIA) was established in 2019 to drive the national AI strategy in Saudi Arabia. SDAIA's main entities include the National Data Management Office (NDMO), the National Center for AI (NCAI), and the National Information Center (NIC). SDAIA has launched initiatives like the Tuwaiq AI Challenge and the Global AI Summit. Why it matters: SDAIA is central to Saudi Arabia's Vision 2030 plan to diversify the economy and develop AI capabilities.