arXiv:2503.05542v4 Announce Type: replace Abstract: We consider standard gradient descent, gradient flow and conjugate gradients as iterative algorithms for minimising a penalised ridge criterion in linear regression. While it is well known that conjugate gradients exhibit fast numerical convergence, the statistical properties of their iterates are more difficult to assess due to inherent non-linearities and dependencies. On the other hand, standard gradient flow is a linear method with well-known regularising properties when stopped early. By an explicit non-standard […]

Ver mais

arXiv:2601.21868v1 Announce Type: new Abstract: Understanding the stability and long-time behavior of generative models is a fundamental problem in modern machine learning. This paper provides quantitative bounds on the sampling error of score-based generative models by leveraging stability and forgetting properties of the Markov chain associated with the reverse-time dynamics. Under weak assumptions, we provide the two structural properties to ensure the propagation of initialization and discretization errors of the backward process: a Lyapunov drift condition and a […]

Ver mais

arXiv:2602.11174v1 Announce Type: new Abstract: Pretrained multilingual language models are often assumed to be script-agnostic, yet their tokenizers can impose systematic costs on certain writing systems. We quantify this script tax by comparing two orthographic variants with identical linguistic content. Across mBERT and XLM-R, the higher-fragmentation orthography shows a ~3.4x increase in fertility (6.73-6.85 vs. 2.10-2.35 tokens/word), leading to a 16.5x inference slowdown (0.23 vs. 3.8 sentences/second) on identical hardware. Using bits per character (BPC) to avoid the […]

Ver mais

arXiv:2302.00941v4 Announce Type: replace-cross Abstract: We propose a novel statistical learning method for multi-item auctions that incorporates credible intervals. Our approach employs nonparametric density estimation to estimate credible intervals for bidder types based on historical data. We introduce two new strategies that leverage these credible intervals to reduce the time cost of implementing auctions. The first strategy screens potential winners’ value regions within the credible intervals, while the second strategy simplifies the type distribution when the length of […]

Ver mais

arXiv:2505.21813v2 Announce Type: replace-cross Abstract: Data Augmentation (DA) has become an essential tool to improve robustness and generalization of modern machine learning. However, when deciding on DA strategies it is critical to choose parameters carefully, and this can be a daunting task which is traditionally left to trial-and-error or expensive optimization based on validation performance. In this paper, we counter these limitations by proposing a novel framework for optimizing DA. In particular, we take a probabilistic view of […]

Ver mais

arXiv:2510.21091v2 Announce Type: replace Abstract: Algorithmic fairness is a socially crucial topic in real-world applications of AI. Among many notions of fairness, subgroup fairness is widely studied when multiple sensitive attributes (e.g., gender, race, age) are present. However, as the number of sensitive attributes grows, the number of subgroups increases accordingly, creating heavy computational burdens and data sparsity problem (subgroups with too small sizes). In this paper, we develop a novel learning algorithm for subgroup fairness which resolves […]

Ver mais

When I first thought about this article, I had planned to go with a headline ‘Harness Matters’ or something cool like ‘A good harness is all you need’, but to my own shock, it seems to not actually make that much of an impact – atleast as far as MVP’ing a front end wireframe goes. Maybe much further down the line it might matter more than this and compounds on varying abilities present in each of them, but […]

Ver mais

arXiv:2602.21343v1 Announce Type: new Abstract: Decentralized Federated Learning (DFL) eliminates the need for a central aggregator, but it can expose communication patterns that reveal participant identities. This work presents UnlinkableDFL, a DFL framework that combines a peer-based mixnet with fragment-based model aggregation to ensure unlinkability in fully decentralized settings. Model updates are divided into encrypted fragments, sent over separate multi-hop paths, and aggregated without using any identity information. A theoretical analysis indicates that relay and end-to-end unlinkability improve […]

Ver mais