Category
3,017 papers
This paper derives oracle risk bounds for learning dense and sparse routing with evolving experts, separating approximation, expert-learning, and router-estimation errors, and characterize how sparse Top-K routing can retain the benefits of localized aggregation while controlling per-input computation.
This work proposes Adaptive Local Relational Alignment (ALRA), a position-specific framework combining student proposals with teacher guidance, which replaces the teacher-mass coefficients of the two conditional terms with unit coefficients, preventing either term from being downweighted solely because its region has l...
A high-probability uniform ($L^{\infty}$) recovery guarantee that jointly controls approximation and statistical errors while enjoying an optimization error of zero is introduced.
Occupancy-based Quantile Risk Control (OQRC), a novel method that provides tight risk control bounds with finite-sample validity and establishes a finite-sample guarantee showing that OQRC yields tight risk control bounds that converge to the optimal bounds at a provable rate of $\mathcal{O}_ p(n^{-1/2})$.
Reach audiences
Advertise in front of researchers, engineers, and readers.
Many NLP tasks, such as summarization and extractive question answering, reduce to retrieving relevant content from documents under two constraints: coverage, retaining enough pertinent information to achieve some goal, and conciseness, removing as much irrelevant information as possible. Conformal prediction methods h...
A statistical feature augmentation method that explicitly encodes behavioral interaction statistics into the input feature space and consistently improves detection performance is proposed, showcasing a promising approach for merging classical network analysis with deep learning.
A mean-field RL framework is introduced in which the rewards and transition dynamics depend on the population only through an unknown low-dimensional aggregate statistic, and it is shown that under a fixed neural-network parameter count and optimization budget, learning a low-dimensional population representation impro...
This work studies attention-indexed models, a broad framework that can represent multi-layer and multi-head attention architectures, and reveals that attention parameterization itself can act as an architectural implicit bias.
Experimental results suggest that the parameters of trained autoencoders can be viewed as sample representations, allowing for a high degree of accuracy in distinguishing between models trained on different data subsets, without resorting to complex vector generation algorithms or using the original samples.
Causal foundation models are pretrained neural networks that estimate causal quantities, such as the average treatment effect, on entirely new datasets using in-context learning without requiring model updates.
Finite-Library Input-Warped Bayesian Optimization (FLIWBO), which selects warps from a finite library of smooth input maps by any history-dependent rule, and adapts the input geometry to accelerate learning while retaining high-probability convergence guarantees under mild hypotheses, with an explicit library-size cost...
Learned graph simulators provide an efficient alternative to high-fidelity solvers for granular dynamics. However, granular motion depends strongly on inter-granular contact history, which is difficult to preserve when particle contacts form, break, and rearrange. Existing simulators mainly store temporal information i...
Accelerating the search for novel antimicrobial peptides using Google Antigravity for Science.
Zero-knowledge proofs can verify computing results without rerunning workloads or exposing sensitive data. Magnetar helps bring them into the mainstream with support for standard programming languages, major speed gains, and quantum-resistant security. The post Proof-based general-purpose computing with Magnetar appeared first on Microsoft Research.
General Science
General Science
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.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
