RR dominates SGD in smooth convex optimization under any reasonable stepsize after any finite number of epochs.
Mixed citations
A Stochastic Approximation Method,
Mixed citation behavior. Most common role is background (62%).
94
Pith papers citing it
Background
62% of classified citations
citation-role summary
background 10
method 3
citation-polarity summary
representative citing papers
Presents a deterministic minimax-optimal multicalibration algorithm and its generalization to outcome indistinguishability and omniprediction, resolving open questions on randomization necessity.
Manifold curvature and intrinsic dimension predict layerwise SAE width exponents and asymptotic floors across Gemma models, with cross-model transfer of the geometric regression, establishing a transferable geometric law instead of a universal scaling law.
Steered LLM activations are non-surjective: under practical assumptions, they lie outside the set of states reachable from any discrete prompt.
The paper derives quantum-optimal spatial modes for mode-sorting coronagraphy that account for finite star size and complex apertures, improving detection performance at close working angles.
Direct fixed-weight solver for free-support Wasserstein medians relocates atoms using OT barycentric projections and inverse-distance weights, achieving monotone descent on smoothed objectives with fewer subproblems than nested Weiszfeld baselines.
EFE-based planning is formulated as variational free energy minimization with epistemic priors, decomposing into expected plan costs plus a complexity term.
The paper shows that arbitrage-free information pricing is computationally hard in general, provides a branch-and-bound algorithm, and proves that for threshold utilities arbitrage-freeness reduces to Blackwell dominance, unifying prior query and model pricing results.
EFE-based active inference planning is characterized as VFE on an augmented model plus entropy and planning corrections, with a derived message-passing implementation and grid-world validation.
The paper introduces a protocol-resolved framework for virological measurements, defining an observation operator that maps latent ensembles to observed data and recasting plaque assays as estimates of protocol-conditioned infectious concentration.
Proposes a scale-calibrated median-of-means estimator for robust aggregation of distributed PCA estimates on the product of Euclidean space and Grassmann manifold.
Derives the asymptotic distribution of the spatial Cramér-von Mises independence statistic under β-mixing on R² and implements it in Python with eigenvalue-based critical values.
A 10-qubit convolutional quantum graph neural network fed by autoencoder-compressed jet data achieves performance comparable to classical graph networks in distinguishing boosted Z jets from gluon jets.
A new differentiable reconstruction method uses symmetrized hyperspherical harmonics on quaternions plus two- and three-point descriptors to generate 3D microstructures from 2D data, demonstrated on aluminum alloy with L-BFGS-B optimization.
The test error of random-feature ridge regression with arbitrary data augmentation admits a closed-form asymptotic characterization in the proportional regime that depends only on population covariances and augmentation statistics.
Time-reversed Young interferometry acts as a source-space information processor where mutual information is the reciprocal invariant and source-label entropy can decrease near destructive interference while Fisher information rises.
Three new provably KL-optimal frequency normalization algorithms are presented, one running in linear time in the number of symbols.
The profile maximum likelihood estimator for the location in anisotropic hyperbolic wrapped normal models is strongly consistent, asymptotically normal, and attains the Hájek-Le Cam minimax lower bound under squared geodesic loss.
Exponentially-shifted Gaussian smoothing yields zeroth-order gradient estimators with linear dimension dependence, enabling improved complexity bounds for stochastic optimization including decision-dependent regimes.
VGF solves behavior-regularized RL by transporting particles from a reference distribution to the value-induced optimal policy via discrete value-guided gradient flow.
The normalized sum of negative log-likelihoods under sublinear parsings converges almost surely and in L1 to the entropy rate h_P for any shift-invariant measure on a finite shift space.
Statistical Linkage Learning enables a new mask construction algorithm for Partition Crossover that maintains effectiveness on noisy problems with hidden dependencies and matches noise-free performance when decomposition quality is high.
ManyIH and ManyIH-Bench address instruction conflicts in LLM agents with up to 12 privilege levels across 853 tasks, revealing frontier models achieve only ~40% accuracy.
A meta-learning method identifies the conditional mean of task-specific causal demand parameters by conditioning on all prices while masking two demand outcomes, assuming at least two locally exogenous prices per task.
citing papers explorer
-
Steered LLM Activations are Non-Surjective
Steered LLM activations are non-surjective: under practical assumptions, they lie outside the set of states reachable from any discrete prompt.
-
Expected Free Energy-based Planning as Variational Inference
EFE-based planning is formulated as variational free energy minimization with epistemic priors, decomposing into expected plan costs plus a complexity term.
-
What Type of Inference is Active Inference?
EFE-based active inference planning is characterized as VFE on an augmented model plus entropy and planning corrections, with a derived message-passing implementation and grid-world validation.
-
When Outcome Looks Right But Discipline Fails: Trace-Based Evaluation Under Hidden Competitor State
The paper introduces discipline stability, a trace-based evaluation paradigm for checking if RL agents maintain behavioral discipline like rule-based competitors in hidden-state competitive settings such as hotel pricing and bidding.
-
Scaling Laws for Task-Specific LLM Distillation
Empirical scaling laws for task-specific LLM distillation in quantitative finance indicate that chain-of-thought supervision recovers general knowledge lost during iterative pruning while in-domain performance degrades predictably.
-
PRISMat: Policy-Driven, Permutation-Invariant Autoregressive Material Generation
PRISMat generates crystal slabs with mean absolute errors of 0.188 eV/A² for cleavage energy and 2.79 eV for work function, reducing error by 4× versus the next best model while using less inference time.