February 2026

Muon updates matrix parameters via the matrix sign of the gradient and has shown strong empirical gains, yet its dynamics and scaling behavior remain unclear in theory. We study Muon in a linear associative memory model with softmax retrieval and a hierarchical frequency spectrum over query-answer pairs, with and without label noise. In this setting, we show that Gradient Descent (GD) learns frequency components at highly imbalanced rates, leading to slow convergence bottlenecked by low-frequency components. In contrast, […]

Ver mais

Federated Learning is a privacy-preserving decentralized approach for Machine Learning tasks. In industry deployments characterized by a limited number of entities possessing abundant data, the significance of a participant’s role in shaping the global model becomes pivotal given that participation in a federation incurs costs, and participants may expect compensation for their involvement. Additionally, the contributions of participants serve as a crucial means to identify and address potential malicious actors and free-riders. However, fairly assessing individual contributions remains […]

Ver mais

Ads are inevitable when you are on the internet. These days, Google Search is filled with sponsored results. Although AI has taken over our lives and how we browse the internet, ads are not leaving our backs. Earlier this month, OpenAI revealed its plans to display ads for users in the US on ChatGPT Free and Go plans. For the uninitiated, ChatGPT Go is now also live in the US, after initially debuting in the Indian and Indonesian […]

Ver mais

Structural shifts pose a significant challenge for graph neural networks, as graph topology acts as a covariate that can vary across domains. Existing domain generalization methods rely on fixed structural augmentations or training on globally perturbed graphs, mechanisms that do not pinpoint which specific edges encode domain-invariant information. We argue that domain-invariant structural information is not rigidly tied to a single topology but resides in the consensus across multiple graph structures derived from topology and feature similarity. To […]

Ver mais

Blockchain technology is no longer just the backbone of cryptocurrencies; it has become a powerful tool for real businesses. In a world still reeling from supply-chain disruptions and data breaches, blockchain promises to reinvent trust in multi-party systems. As Deloitte notes, “using blockchain can improve both supply chain transparency and traceability” while cutting costs. Kevin Werbach of Wharton puts it succinctly: “Blockchain is not the end of trust. Blockchain is a new structure of trust, a ‘new architecture […]

Ver mais