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.

169,291 papers · 148 categories

Trend · papers per month

76153229305 · Jun 202019922001200920182026
48 results for strongly adaptive

New online conformal prediction methods minimize strongly adaptive regret and achieve near-optimal coverage.

problem Uncertainty quantification in online settings with changing data distributions.
method Developed new online conformal prediction methods that minimize strongly adaptive regret.
result Achieve near-optimal strongly adaptive regret and approximately valid coverage.

SA algorithms control dynamic regret in non-stationary settings with strong convexity or exp-concavity.

problem Non-stationary Online Convex Optimization with dynamic regret control.
method Strongly Adaptive (SA) algorithms view dynamic regret as path variation of the comparator sequence.
result SA algorithms achieve ildeO(TVTlogT) ilde O(\sqrt{TV_T} \vee \log T) and ildeO(dTVTdlogT) ilde O(\sqrt{dTV_T} \vee d\log T) dynamic regret for strongly convex and exp-concave losses, respectively.

New algorithms minimize dynamic regret for strongly convex losses.

problem Minimizing dynamic regret for strongly convex losses.
method Developed Strongly Adaptive algorithms exploiting KKT conditions.
result Achieved near optimal dynamic regret of O(d1/3n1/3extTV[u1:n]2/3d)O(d^{1/3} n^{1/3} ext{TV}[u_{1:n}]^{2/3} \vee d).

Paper analyzes and improves adaptive gradient methods for optimization.

problem Improving optimization methods for deep neural networks.
method Analyzes and proposes variants of RMSProp and Adagrad for online convex optimization.
result Proposes SC-Adagrad and SC-RMSProp with logarithmic regret bounds for strongly convex functions.

Unintended effects from scaling neural network outputs with adaptive learning rates.

problem Adaptive learning rate optimization's behavior is altered by output scaling, leading to misinterpretation.
method Presented a modified optimization algorithm to mitigate unintended effects.
result Adaptive learning rate's effectiveness is significantly impacted by output scaling, especially for small scaling factors.

Improved SHB method for faster convergence on strongly-convex quadratics.

problem Understanding and improving the theoretical and practical advantages of SHB.
method Noise-adaptive multi-stage algorithm for SHB with accelerated convergence.
result SHB can achieve accelerated convergence with larger mini-batch sizes.

Adaptive step sizes improve optimization for convex and nonconvex problems.

problem Optimizing functions that are not strongly convex.
method Bridge nonconvex and strongly convex problems via regularization, then apply Barzilai-Borwein step sizes with SARAH.
result Regularized SARAH methods achieve better complexity in nonconvex problems.

Investigates connections adapted to a holomorphic Lie group action on bundles.

problem Finding connections adapted to a Lie group action on bundles.
method Analyzes connections on principal HH-bundles over complex manifolds with holomorphic actions of Lie groups.
result Identifies conditions for connections to be adapted to a given GG-connection.

Upper and lower bounds derived for online learning with graph-structured feedback against adaptive adversaries.

problem Online learning with graph-structured feedback against adaptive adversaries.
method Analysis of Exp3 algorithm variants and lower bounds for specific adversary models.
result Upper bounds of O~(T2/3)\widetilde O(T^{2/3}) and O~(T3/4)\widetilde O(T^{3/4}) for strongly-observable and weakly-observable graphs, respectively.

This paper analyzes adaptive gradient algorithms for better performance in ill-conditioned problems.

problem Poor performance of standard stochastic gradient algorithms in ill-conditioned problems.
method Non-asymptotic analysis of adaptive gradient algorithms (Adagrad and Stochastic Newton) for strongly convex objectives.
result Theoretical analysis and adaptation to practical applications like linear regression and regularized GLM.

Optimal online linear regression in dynamic environments using discounted Vovk-Azoury-Warmuth forecaster.

problem Achieving optimal performance in dynamic online linear regression without prior knowledge.
method Developed a discounted variant of the Vovk-Azoury-Warmuth forecaster to achieve optimal dynamic regret guarantees.
result Achieved dynamic regret of the form $O\left(d\log(T)\vee \sqrt{dP_{T}^γ(\vec{u})T} ight)$, with a learnable discount factor.

The study shows strong formality in certain complex manifolds.

problem Investigating strong formality in complex manifolds.
method Adapting ss-strong formality from Fernandez and Muñoz to the pluripotential setting.
result Compact Kähler manifolds and generalized complete intersections are strongly formal.

Random extrapolation speeds up coordinate descent for sparse and dense data.

problem Efficiently solving primal-dual coordinate descent for sparse and dense data.
method Adapts to sparsity and uses large step sizes for dense data, proving linear convergence under metric subregularity.
result Linear convergence under metric subregularity and optimal sublinear convergence rates in general convex-concave problems.

Adaptive personalized federated learning improves local model personalization.

problem Maximizing global model performance limits local model personalization.
method APFL algorithm trains local models while contributing to global model, with optimal mixing parameter and communication-efficient optimization.
result Demonstrates effectiveness of personalization schema and correctness of generalization theories.

TiAda adapts adaptive gradient methods for nonconvex minimax optimization.

problem Nonconvex minimax optimization challenges in achieving convergence.
method TiAda is a time-scale adaptive GDA algorithm for nonconvex minimax optimization.
result TiAda achieves near-optimal complexities in deterministic and stochastic settings.

Three adaptive methods improve financial forecasting and portfolio management.

problem Improving financial forecasting and portfolio management in volatile markets.
method Dynamic Model Selection (DMS), Adaptive Ensemble (AE), Dynamic Asset Allocation (DAA).
result Adaptive methods outperform long-only benchmarks in US market returns.

New method achieves both universality and adaptivity in online convex optimization.

problem Achieve optimal regret guarantees without prior knowledge of function curvature.
method Introduces UniGrad, a novel approach that achieves both universality and adaptivity.
result Achieves universal regret guarantees that adapt to gradient variation.

Introduces CSLC models to bridge deep generative models and classical algorithms.

problem Mode collapse and memorization issues in deep generative models and restrictive assumptions in classical algorithms.
method Introduces conditionally strongly log-concave (CSLC) models, factorizing data distribution into strongly log-concave conditional distributions.
result Efficient parameter estimation and sampling algorithms with theoretical guarantees for non-log-concave data distributions.

A Kernel Adaptive Metropolis-Hastings algorithm is introduced, for the purpose of sampling from a target distribution with strongly nonlinear support. The algorithm embeds the trajectory of the Markov chain into a reproducing kernel Hilbert space (RKHS), such that the feature space covariance of the samples informs the…

2013-07-19abs ↗pdf ↗

Compactifies SU(2) monopole moduli spaces, proving part of Sen's conjecture.

problem Proving part of Sen's conjecture for L2 cohomology of moduli spaces.
method Compactifications of moduli spaces of SU(2) monopoles on R3, leading order asymptotic expansions of hyperKaehler metrics.
result Proves part of Sen's conjecture for the L2 cohomology of strongly centered moduli spaces.

Adaptive sampling method reduces variance in stochastic optimization.

problem Reducing variance in stochastic optimization with limited gradient computations.
method Adaptive increase in sample size based on inner product test.
result Algorithm converges globally on nonconvex functions and linearly on strongly convex functions.

We consider the problems of detection and localization of a contiguous block of weak activation in a large matrix, from a small number of noisy, possibly adaptive, compressive (linear) measurements. This is closely related to the problem of compressed sensing, where the task is to estimate a sparse vector using a small…

2012-09-15abs ↗pdf ↗

Universal algorithm minimizes adaptive regret for various convex functions.

problem Minimizing adaptive regret in changing environments for multiple convex functions.
method Borrowing MetaGrad's idea of multiple learning rates and using sleeping experts.
result First universal algorithm for minimizing adaptive regret of convex functions.

FDN improves probabilistic regressors' adaptability to distribution shifts.

problem Overconfidence in modern probabilistic regressors under distribution shift.
method FDN uses input-conditioned distributions over network weights, trained with a Monte Carlo beta-ELBO objective.
result FDN produces predictive mixtures whose dispersion adapts to the input, providing shift-aware uncertainty.

Gaussian Mixture Models (GMM) have found many applications in density estimation and data clustering. However, the model does not adapt well to curved and strongly nonlinear data. Recently there appeared an improvement called AcaGMM (Active curve axis Gaussian Mixture Model), which fits Gaussians along curves using an …

2015-02-06abs ↗pdf ↗

Researchers adaptively analyze market regimes to reveal investor behavior shifts.

problem Market relationships shift across different regimes, affecting investor behavior.
method Combining Kalman filtering, Markov-switching, and asymmetric response estimation.
result Foreign investors' predictive power increases during crises, while individual investors react more strongly to positive shocks.

Adaptive method improves numerical solution of Cox-Ingersoll-Ross model.

problem Approximating solutions to the Cox-Ingersoll-Ross model efficiently.
method Path-bounded timestepping with hybrid approach, including a backstop method.
result The adaptive method is strongly convergent, with strong error control.

An adaptive algorithm optimizes resource allocation with diminishing returns.

problem Sequential resource allocation with diminishing returns.
method Adaptive stochastic optimization algorithm that minimizes regret.
result Optimizes cumulative reward with optimal rates for strongly-concave functions and classical multi-armed bandit rates.

ESS improves MCMC efficiency for correlated & multimodal distributions.

problem Slice Sampling's sensitivity to initial length scale and difficulty with correlated distributions.
method Adaptive tuning and parallel walkers for efficient sampling.
result ESS improves efficiency by more than an order of magnitude on correlated distributions.

New insights show NAG and FISTA converge linearly without knowing strong convexity modulus.

problem Understanding linear convergence of NAG and FISTA without strong convexity modulus knowledge.
method High-resolution ODE framework, dynamically adapting kinetic energy coefficient.
result NAG and FISTA demonstrate linear convergence without requiring strong convexity modulus knowledge.