Category
2,952 papers
HiFedProx is introduced, which replaces the quadratic penalty with a scale-matched power-type regularizer indexed by p, and combines this geometry with finite-budget stochastic client optimization and same-minibatch Armijo backtracking.
Muon-C is introduced, an operator-aligned optimizer that represents kernel momentum as frequency-wise channel-transfer matrices, polarizes these blocks independently, and uses a critical Fourier grid to return updates exactly to the original finite kernel support.
Weak Sparse Identification of Nonlinear Dynamics (WSINDy) provides a noise-robust approach for learning dynamical systems from data without requiring numerical differentiation. However, for high-dimensional systems, tensor-product libraries of candidate functions grow exponentially with the state dimension, making stan...
A staged, accountable evaluation protocol that treats the evaluation of a deployed model as a measurement with declared reference levels and a quantified uncertainty and demonstrates the protocol on infrastructure-free geomagnetic localisation with smartphone-based recurrent classifiers in two real underground mines.
Reach audiences
Advertise in front of researchers, engineers, and readers.
A statistical approach to bias rectification that can be combined in a turn-key fashion with any classical GZSL feature learner as a blackbox, thereby suggesting a wide scope of applicability of this method for a wide variety of GZSL implementations in different domains.
This work introduces FlowCPO, an offline forward-KL objective that uses both preferred and dispreferred samples without online rollouts and shows under explicit regularity conditions that the forward-KL objective is bounded by a contrastive flow matching loss, yielding a tractable surrogate on fixed data.
An exact finite-sample necessary-and-sufficient condition for two-stage training to strictly outperform real-only training under the same real-data budget and identical real-stage updates is established.
This work characterize the asymmetry between active and inactive interference and the trade-off between interference and observation-noise budgets and introduces IHT-SAE, which uses learned iterative refinement to improve feature recovery beyond the limits of linear availability.
This work gives an exact, conservative one-coordinate finite-task confidence certificate and a reporting standard separating direct estimates, identified sets, and model-conditioned forecasts, and gives exact count-law-preserving constructions with incompatible extrapolations with incompatible extrapolations.
The edge-of-chaos condition preserves first-order input perturbations in wide randomly initialized networks, but physics-informed losses, score matching and derivative regularization depend on higher input derivatives. For smooth scalar-input fully connected networks, using a joint Gaussianity of the finite derivative...
<!-- release-title: v1.10.0: MCP --> wisp-science v1.10.0 v1.10.0 brings scientific MCP tools into Wisp's native Rust runtime. The bundled catalog provides 23 connectors and 247 tools across roughly 80 upstream databases, with browsable connector introductions and tool parameters. This release also improves first-time...
Bandit algorithms generate data for downstream inference, but adaptive sampling biases post-bandit sample means. We analyze this bias for stable index algorithms, including UCB1 and its generalizations, and derive sharp leading-order expressions for the sample-mean bias and expected $Z$-statistic. Our characterization...
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.
MIT Statistics and Data Science Center Director Alexander (Sasha) Rakhlin shares important considerations for departments and institutions.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
