Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,695 papers · 148 categories

Trend · papers per month

1122 · Sep 201919922001200920172026
28 results for RFM

RFMs transition from linear to nonlinear under specific input-label correlation.

problem Understanding the transition from linear to nonlinear behavior in RFMs.
method Analyzing RFMs under spiked covariance designs, characterizing the interaction between anisotropy and input-label correlation.
result The RFM generalization error is governed by the strength of input-label correlation, leading to a clear nonlinear advantage above a specific boundary.

RFM reduces feature space for linear models, improving sparse recovery.

problem Sparse linear regression and low-rank matrix recovery.
method Recursive Feature Machines (RFM) that alternates between reweighting feature vectors by AGOP and learning prediction function.
result RFM generalizes IRLS and outperforms deep linear networks.

RFM improves CNFs by adding a boundary constraint term and matching velocity fields.

problem Flow matching on constrained domains leads to unnatural samples.
method RFM adds a boundary constraint term and matches velocity fields in a simulation-free manner.
result RFM achieves comparable or better results on standard image benchmarks and produces high-quality samples.

Recursive Feature Machines show grokking in modular arithmetic without neural networks.

problem Grokking in modular arithmetic tasks.
method Recursive Feature Machines (RFM) with Average Gradient Outer Product (AGOP).
result RFM and neural networks learn block-circulant features to solve modular arithmetic.

FlowChef steers RFMs to efficiently guide image generation tasks.

problem Efficiently guiding image generation tasks with RFMs.
method Developed a theoretical and empirical understanding of RFMs' vector field dynamics, proposing FlowChef for gradient-free navigation.
result FlowChef significantly outperforms baselines in performance, memory, and time requirements.

RFM uses tangent vector fields to match data on manifolds, analyzing TV convergence for Euler discretization.

problem Matching data on curved manifolds using flow-based models.
method Developed a nonasymptotic TV convergence analysis for RFM samplers using Euler discretization.
result Explicit bounds on TV convergence separating numerical discretization and learning errors.

Hybrid regularization avoids double descent in random feature models.

problem Avoiding the double descent phenomenon in random feature models.
method Combines early stopping and weight decay, using GCV for hyperparameter selection.
result Hybrid method successfully avoids double descent and achieves comparable generalization.

Breaking symmetry in training data is key for generalization in feature learning kernels.

problem Grokking in algebraic tasks, where models perform well on training but fail on unseen data.
method Used Recursive Feature Machine (RFM) with AGOP to learn task-relevant features, breaking symmetry in training data.
result Generalization occurs only when symmetry in the training set is broken, and RFM generalizes by recovering underlying invariance group action.

The behavioral dynamics of multi-agent systems have a rich and orderly structure, which can be leveraged to understand these systems, and to improve how artificial agents learn to operate in them. Here we introduce Relational Forward Models (RFM) for multi-agent learning, networks that can learn to make accurate predic…

2018-09-28abs ↗pdf ↗

We analyze random feature and two-layer neural networks using duality framework.

problem Understanding and analyzing functions within Fp,π\mathcal{F}_{p,π} and Barron spaces.
method Duality framework based on information-based complexity (IBC).
result Sharp bounds for learning Fp,π\mathcal{F}_{p,π} using RFMs without curse of dimensionality for p>1p>1.

RG-VFM extends VFM to curved manifolds for better material and protein design.

problem Designing materials and proteins on curved manifolds.
method Riemannian Gaussian Variational Flow Matching (RG-VFM) for generative modeling on manifolds.
result RG-VFM more effectively captures manifold structure and improves performance.

FlowLLM uses LLMs and flow matching to efficiently generate novel materials.

problem Challenging material discovery due to vast chemical space.
method Combines LLMs and Riemannian flow matching to design novel crystalline materials.
result Significantly increases generation rate of stable materials and unique crystals.

Sp(n)-instantons linked to complex Lagrangian graphs via Fourier-Mukai transform.

problem Understanding Sp(n)-instantons on hyperkahler manifolds with conical singularities.
method Relating Sp(n)-instantons to deformed instantons and studying their properties on hyperkahler manifolds.
result Sp(n)-instantons on hyperkahler manifolds correspond to tri-contact instantons on the 3-Sasakian link.

WaveCRN improves E2E speech enhancement with efficient CNN and SRU.

problem Efficiently modeling speech locality and sequential properties for E2E speech enhancement.
method WaveCRN uses a CNN for speech locality and SRU for temporal sequential modeling, with RFM for noise suppression.
result WaveCRN outperforms state-of-the-art approaches with reduced complexity and inference time.

Unified analysis of reweighted least-squares algorithms for linear models.

problem Recovering unknown signals from linear measurements using reweighted least squares.
method Unified asymptotic analysis of IRLS, lin-RFM, and alternating minimization algorithms.
result The algorithms can achieve favorable performance in a few iterations with appropriate reweighting.

SGD noise helps select flat minima by concentrating in sharp directions and being proportional to loss value.

problem Understanding the implicit regularization of SGD and selecting flat minima in over-parameterized models.
method Relating SGD's linear stability to the Frobenius norm of the Hessian and analyzing the alignment property of SGD noise.
result Flat minima are linearly stable for SGD, and their sharpness is bounded independently of model size and sample size.

AGOP from KRR recovers central subspace in fewer samples than needed for prediction.

problem Recovering low-dimensional structure in multi-index polynomial functions.
method Fit kernel ridge regression and compute AGOP from the fitted predictor.
result AGOP's top rr eigenspace recovers the central subspace in ndp+δn \asymp d^{p+δ} samples.