Despite its ubiquity, clustering lacks a universally accepted definition of what is a cluster. Kleinberg's Impossibility Theorem formalizes this difficulty by showing that no flat clustering method can simultaneously satisfy three natural axioms: scale invariance, richness, and consistency. In this paper, we ask whethe...
Daichi Kuroda, Maximilien Dreveton, Matthias Grossglauser et al.· 0 citations
It is proved that an unbounded gap between the update maps can coexist with vanishing predictive KL for every fixed finite $K\ge2$ in a stationary symmetric Gaussian HMM, and isolates two missing links between internal update gaps and predictive cost.
Qi-Fu Wen, Shuai Liu, Zihan Zhou et al.· 0 citations
Unlabeled-unlabeled (UU) learning allows us to learn a binary classifier from two sets of unlabeled data with different class-priors. It is a general framework because it includes a wide variety of supervised learning such as positive-unlabeled (PU) learning, noisy label learning, and similarity-based learning. Existin...
Atsutoshi Kumagai, Tomoharu Iwata, Hiroshi Takahashi et al.· 0 citations
This paper studies the bipartite architecture of Krotov and Hopfield, whose model is fixed by a Lagrangian for each layer, taking the hidden neurons as the order parameter of retrieval, and splits retrieval into two roles, the visible Lagrangian fixing stability and the hidden one the storage scale.
Toshihiro Ota, M. Taki· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
This paper derives an estimator of the AUC risk using biased PU data with confidence, enabling AUC maximization under such bias, and shows that the rewritten AUC risk induces a Bayes-optimal AUC ranking even when the available confidence is any strictly increasing transformation of the true posterior probability.
Atsutoshi Kumagai, Tomoharu Iwata, Hiroshi Takahashi et al.· 0 citations
We continue the study of relatively smart learning, introduced by Dughmi and Pour (2026), which asks a supervised learner to compete, marginal by marginal, with every distribution-fixed error guarantee soundly certifiable from unlabeled data. They showed that the One-Inclusion Graph (OIG) learner is relatively smart wi...
This work proves that incremental learning still occurs, and introduces a symmetry-based finite-width approximation via symmetrized networks, rather than comparing directly with an infinite-width limit, which yields better control of approximation errors and may be of independent interest.
Continuous and discrete flow matching are usually treated as separate constructions. This paper identifies a duality between them: projecting continuous convex-interpolant paths with one-hot targets through a position-wise argmax yields discrete convex-interpolant paths. The result requires source laws with appropriate...
Across CIFAR-100-C, Tiny-ImageNet-C, and SEN12MS, this work shows reliable target-domain coverage transfer without labeled target calibration data, with label-free diagnostics that predict when correction is needed.
Food structure and its effect on deformation behaviour and sensory perception is still a challenge in food science. Small-Amplitude Oscillatory Shear (SAOS) is a common method for the determination of the linear viscoelastic properties and stability of food materials, but it is not applicable to large deformations, suc...
It is argued that a third, largely untapped signal is both richer and more principled: critical adjacency, the pairwise relation established when an expert critic explicitly links two artists in long-form prose, which offers both a scalable cold-start discovery mechanism and a sociological grounded approach to MIR and...
We develop a reinforcement learning pipeline for simplifying knot diagrams. A trained agent learns move proposals and a value heuristic for navigating Reidemeister moves. The pipeline applies to arbitrary knots and links; we test it on ``very hard'' unknot diagrams and, using diagram inflation, on $4_1\#9_{10}$ where w...
Anne Dranowski, Yura Kabkov, Daniel Tubbenhauer· 0 citations
Learn how Google DeepMind and GovTech Singapore uses lightweight on-device Gemma models to intercept conversational scams in private chats with zero cloud data egress.
MIT News · Artificial Intelligence· news.mit.eduOct 8, 2026
