Search

Results for "Samuel Horváth"

KAUST master’s degree student wins best poster award at Data Science Summer School

KAUST · Oct 11

KAUST master’s degree student Samuel Horváth won a best poster award at the Data Science Summer School (DS3) in Paris for his poster entitled "Nonconvex Variance Reduced Optimization with Arbitrary Sampling". The poster is based on a paper of the same name currently under review and is joint work between Horváth and his supervisor Professor Peter Richtárik from the KAUST Visual Computing Center. Horváth's research interests are at the interface of statistical learning and big data optimization, with a focus on randomized methods for non-convex problems. Why it matters: This award recognizes the quality of KAUST's research and its students' contributions to the field of data science and optimization.

Orchestrated efficiency: A new technique to increase model efficiency during training

MBZUAI · Invalid Date

MBZUAI's Samuel Horváth presented a new framework called Maestro at ICML 2024 for efficiently training machine learning models in federated settings. Maestro identifies and removes redundant components of a model through trainable decomposition to increase efficiency on edge devices. The approach decomposes layers into low-dimensional approximations, discarding unused aspects to reduce model size. Why it matters: This research addresses the challenge of running complex models on resource-constrained devices, crucial for expanding AI applications while preserving data privacy.

Powerful predictions and privacy

MBZUAI · Invalid Date

MBZUAI Assistant Professor Samuel Horváth is researching federated learning to address the tension between data privacy and the predictive power of machine learning models. Federated learning trains models on decentralized data, keeping sensitive information on devices. Horváth's research focuses on designing algorithms that can efficiently train on distributed data while respecting user privacy. Why it matters: This work is crucial for advancing AI in sensitive domains like healthcare, where privacy regulations limit centralized data collection.