Multiple instance learning (MIL) is widely used in computational pathology because it enables weakly supervised analysis of whole-slide images (WSIs) without requiring patch-level annotations. In attention-based MIL, instances with high attention scores are often interpreted as diagnostically important regions and used...
Noriaki Hashimoto, Shuichi Nishino, Teruyuki Katsuoka et al.· 0 citations
We study the minimum number of hidden neurons required for arbitrary-accuracy approximation of multivariate H\"older-continuous functions on $[0,1]^d$ and the associated encoding complexity. For $d\geq 2$, we construct a fixed, explicitly defined activation function for which a closed-form network with two hidden layer...
Joint-embedding predictive architectures enable planning with latent world models, but accurate transition prediction alone does not ensure that the planning objective is easy to optimize. We introduce Control-Geometry Straightening (CGS), a single auxiliary loss that learns planner-friendly representations by directly...
Simplex Diffusion Models (SDMs) are proposed, a framework that lifts the diffusion process to the probability simplex to represent beliefs over categories and can carry uncertainty across denoising steps, which mitigates information collapse.
Justin Deschenaux, Alexandre Galashov, Andrew Campbell et al.· 1 citation
Reach audiences
Advertise in front of researchers, engineers, and readers.
Many learning tasks map an input distribution to an output distribution. A natural way to model such an operator is to transform each input sample using a continuous function that may depend on the entire input distribution, and then take the distribution of the transformed samples. This defines a measure-dependent pus...
Takashi Furuya, Nicholas H. Nelsen, Frank Cole· 0 citations
We study post-hoc refinement of frozen node classifiers: given only the graph $G$ and class distributions $Q$ predicted by a frozen model, can we improve accuracy without access to node features, model parameters, or gradients? APPNP answers this by propagating logits with a restart towards the initial predictions, min...
Preben Johnsen Bentdal, Nello Blaser, Xue-Cheng Tai· 0 citations
Long contexts are central to modern transformer systems, but most expressivity results choose a different network for each fixed sequence length. We study whether one masked transformer can approximate causal token-to-token maps uniformly over sequences of arbitrary length sampling a fixed normalized horizon. To relate...
Takashi Furuya, Maarten V. de Hoop, Gabriel Peyré· 0 citations
This work investigates conditions that ensure fast transfer in the growing-horizon regime of hyperparameter transfer in a shallow linear network with a single trainable hidden matrix, trained by full-batch gradient descent.
We study approximate sampling: given $N$ independent samples from a proposal distribution $\mu$, the goal is to select one whose distribution is close to a target $\pi$ specified only up to a normalizing constant. Block and Polyanskiy (2023) provide finite budget error bounds for approximate rejection sampling (RS) as...
Off-policy evaluation is a foundational component of offline reinforcement learning, aiming to assess and optimize policy performance using pre-collected datasets. However, such datasets often suffer from pronounced challenges, including distribution shift, $Q$-value overestimation, and low sample utilization efficienc...
Li-Can Kang, Jerry Zhijian Yang, Cheng Yuan et al.· 0 citations
Non-stationary online learning has attracted much attention in recent years, as static regret is insufficient to guide algorithm design in changing environments. To address this limitation, interval regret and dynamic regret have been introduced as two representative performance metrics that strengthen static regret in...
Sampling latency compounds in diffusion workflows, where users generate and discard many candidates before keeping one. Surprisingly, the poor outputs of standard few-step samplers do not reflect a lack of reconstruction capacity: by optimizing only the initial noise, frozen 3-4-step samplers can closely reproduce thei...
Jennifer Neville did not want to go into computer science—but that’s exactly where she landed. Neville discusses the starts and stops that led to her professional sweet spot and her work identifying “surprising failures” making it hard for AI to handle complexity. The post What AI gets wrong and what failure teaches us appeared first on Microsoft Research.
