Category
3,686 papers
We study geometric moment contraction (GMC) of the constant-parameter stochastic Nesterov recursion \[ Y_k=\Theta_k+\beta(\Theta_k-\Theta_{k-1}),\qquad \Theta_{k+1}=Y_k-\gamma G(Y_k,X_{k+1}). \] Under mean strong monotonicity and stochastic $L^p$ Lipschitz continuity, an explicit Perron comparison proves synchronous $L...
The flatness of the loss landscape at a minimizer is a widely used heuristic for reasoning about neural-network generalization, yet evidence for this relation is mostly empirical and controversial, and it is found that the answer strongly depends on the learning task and on the ratio of the number of parameters to the...
This work uses Exponential Tilt Reweighting Alignment (ExTRA), introduced for classification by Maity et al. (2023), to estimate structured distribution shifts and compares using its estimated weights in conformal calibration with additionally tilting the source predictive distribution.
This work proposes a novel trust-region method within the stochastic sequential quadratic programming framework, termed TR-SSQP, which employs a normal-tangential decomposition in the step computation to balance optimality and feasibility and establishes the first asymptotic convergence result for constrained stochasti...
Reach audiences
Advertise in front of researchers, engineers, and readers.
The technique of empirical localization makes it possible to drastically reduce computational cost of the calculation of the normalization constant, and appropriate choice of the deformation for the Bregman divergence can invest the proposed estimator with various kinds of favorable statistical properties, such as effi...
A score-based DAG learning method, named MARCEDES, formulated as an unconstrained score minimization problem, which can be efficiently solved using gradient-based optimization techniques, thereby circumventing the challenges associated with constrained optimization.
A learning-based framework is proposed to replace this MCMC step by reformulating both Gibbs updates as Gaussian denoising problems and implementing them through ODE diffusion, resulting in an alternative to MCMC-based split Gibbs at lower likelihood-update cost.
Stochastic gradient descent for smooth, lower-bounded, possibly nonconvex objectives under distance-dependent conditional moments is studied and unchanged SGD attains the minimax stochastic complexity in this second-moment class.
Together these findings provide concrete, scanner-specific guidance for protocol optimization, with direct implications for reducing acquisition costs and improving the reliability of connectivity-based clinical biomarkers, and provide code enabling researchers to derive principled uncertainty bounds from their own dat...
An end-to-end causal machine learning pipeline designed for real-world applications with continuous treatments that offers a more computationally efficient approach and produces less biased estimates compared to standard methods for problems with continuous treatment and high-dimensional data is presented.
iKFAD is a recently proposed optimiser that replaces adaptive learning rates with adaptive friction in the momentum dynamics, yet performs as well as Adam. Its limitation is that the full friction tensor $\xi\in\mathbb{R}^{m\times n}$ carries the same $\mathcal{O}(mn)$ memory overhead per layer as Adam's second-moment...
Adaptive arm selection changes the distribution of the observations collected by a bandit algorithm, but it need not change their limiting empirical spectrum. We study Gaussian bandit designs in which the dimension and the number of observations grow proportionally. A quantitative coupling theorem compares the design g...
A machine-learning approach called CheMeleon provides a practical way to develop new drugs or other molecules with much less detailed, expensive experimentation.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
Health & Bioscience
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
Data Mining & Modeling
GPT-Lab
· gpt-lab.eu
Nov 3, 2026
Is your company’s AI sovereign? A practical guide for CIOs on AI vendor lock-in, EU Data Act switching, cloud sovereignty, and testing your exit plan before you need it. The post Sovereignty Is the Option to Leave appeared first on GPT-Lab.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
