Searcharxiv⌕ Search

arXiv subjects

Yao Ji

Publications and source records attributed to Yao Ji.

At least 19 recordsLinked to original sources
arXiv2026

Computation of Strong Solutions to Stochastic Variational Inequalities

This paper studies the computation of strong solutions of monotone variational inequalities (VIs) with Lipschitz continuous operators. Building on the idea of accumulative regularization, we develop a general framework for VIs, with particular emphasis on stochastic settings. Under unbiased stochastic oracles with uniformly bounded variance $ \sigma^2$, AR computes an approximate solution with expected operator residual bounded by $\varepsilon$ using at most $ \widetilde{O}\left(\tfrac{LD_0}{\varepsilon}+\tfrac{ \sigma^2}{\varepsilon^2}(\log\tfrac{LD_0}{\varepsilon})^3\right) $ stochastic oracle calls, where $L$ is the Lipschitz constant and $D_0$ bounds the initial distance to the solution. It substantially improves the existing $\mathcal{O}( \sigma^2/\varepsilon^4)$ complexity for residual reduction and matches the lower bound up to logarithmic factors. For strongly monotone VIs, measured by the distance to the solution, AR achieves the optimal oracle complexity when the strong monotonicity modulus is known. By treating the problem as merely monotone, AR still achieves nearly optimal complexity without knowledge of this modulus. We further introduce a state-dependent noise model applicable to general monotone VIs with potentially nonunique solutions, extending state-dependent noise analysis beyond the strongly monotone setting. Under this model, AR, when equipped with an enhanced stochastic operator extrapolation (SOE) method, achieves nearly optimal complexity with the stochastic term depending on the variance at a solution.

math.OC↗
arXiv2026

Stochastic Auto-conditioned Fast Gradient Methods with Optimal Rates

Achieving optimal rates for stochastic composite convex optimization without prior knowledge of problem parameters remains a central challenge. In the deterministic setting, the auto-conditioned fast gradient method has recently been proposed to attain optimal accelerated rates without line-search procedures or prior knowledge of the Lipschitz smoothness constant, providing a natural prototype for parameter-free acceleration. However, extending this approach to the stochastic setting has proven technically challenging and remains open. Existing parameter-free stochastic methods either fail to achieve accelerated rates or rely on restrictive assumptions, such as bounded domains, bounded gradients, prior knowledge of the iteration horizon, or strictly sub-Gaussian noise. To address these limitations, we propose a stochastic variant of the auto-conditioned fast gradient method, referred to as stochastic AC-FGM. The proposed method is fully adaptive to the Lipschitz constant, the iteration horizon, and the noise level, enabling both adaptive stepsize selection and adaptive mini-batch sizing without line-search procedures. Under standard bounded conditional variance assumptions, we show that stochastic AC-FGM achieves the optimal iteration complexity of $O(1/\sqrt{\varepsilon})$ and the optimal sample complexity of $O(1/\varepsilon^2)$.

math.OC↗
arXiv2025

Two-Loop Renormalization-Group Evolution for the Nucleon Distribution Amplitude

We determine for the first time the two-loop renormalization-group (RG) equation for the nucleon light-cone distribution amplitude, which constitutes the last missing ingredient for the complete next-to-leading-logarithmic corrections to the nucleon form factors in the hard-collinear factorization framework. Applying the conformal expansion for this fundamental nucleon distribution amplitude then enables us to construct an analytic solution that captures the desired scale dependence of phenomenologically interesting series coefficients. Importantly, the two-loop RG evolutions of these central hadronic quantities can bring about noticeable impacts on the corresponding leading-logarithmic results for three sample models of the nucleon distribution amplitude.

hep-ph↗
arXiv2025

High-order Accumulative Regularization for Gradient Minimization in Convex Programming

This paper develops a unified high-order accumulative regularization (AR) framework for convex and uniformly convex gradient norm minimization. Existing high-order methods often exhibit a gap: the function-value residual decreases fast, while the gradient norm converges much slower. To close this gap, we introduce AR that systematically transforms the fast function-value residual convergence rate into a fast (matching) gradient norm convergence rate. Specifically, for composite convex problems, to compute an approximate solution such that the norm of its (sub)gradient does not exceed $\varepsilon,$ the proposed AR methods match the best corresponding convergence rate for the function-value residual. We further extend the framework to uniformly convex settings, establishing linear, superlinear, and sublinear convergence of the gradient norm under different lower curvature conditions. Moreover, we design parameter-free algorithms that require no input of problem parameters, e.g., the Lipschitz constant of the $p$-th-order gradient, the initial optimality gap and the uniform convexity parameter, and allow an inexact solution for each high-order step. To the best of our knowledge, no parameter-free methods can attain such a fast gradient norm convergence rate which matches that of the function-value residual in the convex case, and no such parameter-free methods for uniformly convex problems exist. These results substantially generalize existing parameter-free and inexact high-order methods and recover first-order algorithms as special cases, providing a unified approach for fast gradient minimization across a broad range of smoothness and curvature regimes.

math.OC↗
arXiv2025

From Invariant Representations to Invariant Data: Provable Robustness to Spurious Correlations via Noisy Counterfactual Matching

Models that learn spurious correlations from training data often fail when deployed in new environments. While many methods aim to learn invariant representations to address this, they often underperform standard empirical risk minimization (ERM). We propose a data-centric alternative that shifts the focus from learning invariant representations to leveraging invariant data pairs -- pairs of samples that should have the same prediction. We prove that certain counterfactuals naturally satisfy this invariance property. Based on this, we introduce Noisy Counterfactual Matching (NCM), a simple constraint-based method that improves robustness by leveraging even a small number of \emph{noisy} counterfactual pairs -- improving upon prior works that do not explicitly consider noise. For linear causal models, we prove that NCM's test-domain error is bounded by its in-domain error plus a term dependent on the counterfactuals' quality and diversity. Experiments on synthetic data validate our theory, and we demonstrate NCM's effectiveness on real-world datasets.

cs.LG↗
arXiv2025

Regularization Prescription for the Mixing Between Nonlocal Gluon and Quark Operators

It is well-known that in the study of mixing between nonlocal gluon and quark bilinear operators there exists an ambiguity when relating coordinate space and momentum space results, which can be conveniently resolved through Mellin moments matching in both spaces. In this work, we show that this ambiguity is due to the lack of a proper regularization prescription of the singularity that arises when the separation between the gluon/quark fields approaches zero. We then demonstrate that dimensional regularization resolves this issue and yields consistent results in both coordinate and momentum space. This prescription is also compatible with lattice extractions of parton distributions from nonlocal operators.

hep-ph↗
arXiv2025

Extracting Meson Distribution Amplitudes from Nonlocal Euclidean Correlations at Next-to-Next-to-Leading Order

We present the first complete result for the next-to-next-to-leading order (NNLO) hard matching kernel indispensable for a precision extraction of light meson distribution amplitudes from lattice calculations of equal-time nonlocal Euclidean correlation functions. The results are given in both coordinate and momentum space, with the renormalization and matching accomplished in a state-of-the-art scheme. Our results can be used in both large-momentum effective theory and short-distance factorization approaches. Notably, our coordinate space kernel is directly applicable to nonsinglet quark unpolarized and helicity generalized parton distributions as well. We also illustrate the numerical impact of the NNLO matching, using the pion distribution amplitude as an example.

hep-ph↗
arXiv2025

Kinematic power corrections to DVCS to twist-six accuracy

We calculate $(\sqrt{-t}/Q)^k $ and $(m/Q)^k$ power corrections with $k\le 4$, where $m$ is the target mass and $t$ is the momentum transfer, to several key observables in Deeply Virtual Compton Scattering (DVCS). We find that the power expansion is well convergent up to $|t|/Q^2\lesssim 1/4$ for most of the observables, but is naturally organized in terms of $1/(Q^2+t)$ rather than the nominal hard scale $1/Q^2$. We also argue that target mass corrections remain under control and do not endanger QCD factorization for coherent DVCS on nuclei. These results remove an important source of uncertainties due to the frame dependence and violation of electromagnetic Ward identities in the QCD predictions for the DVCS amplitudes in the leading-twist approximation.

hep-ph↗
arXiv2024

Next-to-Next-to-Leading-Order QCD Prediction for the Pion Form Factor

We accomplish for the first time the two-loop computation of the leading-twist contribution to the pion electromagnetic form factor by employing the effective field theory formalism rigorously. The next-to-next-to-leading-order short-distance matching coefficient is determined by evaluating the appropriate $5$-point QCD amplitude with the modern multi-loop technique and subsequently by implementing the ultraviolet renormalization and infrared subtractions with the inclusion of evanescent operators. The renormalization/factorization scale independence of the obtained form factor is then validated explicitly at ${\cal O}(α_s^3)$. The yielding two-loop QCD correction to this fundamental quantity turns out to be numerically significant at experimentally accessible momentum transfers. We further demonstrate that the newly computed two-loop radiative correction is highly beneficial for an improved determination of the leading-twist pion distribution amplitude.

hep-ph↗
arXiv2024

Primitive Quantum Gates for an SU(3) Discrete Subgroup: $Σ(36\times3)$

We construct the primitive gate set for the digital quantum simulation of the 108-element $Σ(36\times3)$ group. This is the first time a nonabelian crystal-like subgroup of $SU(3)$ has been constructed for quantum simulation. The gauge link registers and necessary primitives -- the inversion gate, the group multiplication gate, the trace gate, and the $Σ(36\times3)$ Fourier transform -- are presented for both an eight-qubit encoding and a heterogeneous three-qutrit plus two-qubit register. For the latter, a specialized compiler was developed for decomposing arbitrary unitaries onto this architecture.

hep-lat↗
arXiv2024

Renormalization of the next-to-leading-power $γγ\to h $ and $gg\to h$ soft quark functions

We calculate directly in position space the one-loop renormalization kernels of the soft operators $O_γ$ and $O_g$ that appear in the soft-quark contributions to, respectively, the subleading-power $γγ\to h$ and $gg\to h$ form factors mediated by the $b$-quark. We present an IR/rapidity divergence-free definition for $O_g$ and demonstrate that with a correspondent definition of the collinear function, a consistent factorization theorem is recovered. Using conformal symmetry techniques, we establish a relation between the evolution kernels of the leading-twist heavy-light light-ray operator, whose matrix element defines the $B$-meson light-cone distribution amplitude (LCDA), and $O_γ$ to all orders in perturbation theory. Application of this relation allows us to bootstrap the kernel of $O_γ$ to the two-loop level. We construct an ansatz for the kernel of $O_g$ at higher orders. We test this ansatz against the consistency requirement at two-loop and find they differ only by a particular constant.

hep-ph↗
arXiv2024

On evolution kernels of twist-two operators

The evolution kernels that govern the scale dependence of the generalized parton distributions are invariant under transformations of the $\mathrm{SL}(2,\mathrm R)$ collinear subgroup of the conformal group. Beyond one loop the symmetry generators, due to quantum effects, differ from the canonical ones. We construct the transformation which brings the {\it full} symmetry generators back to their canonical form and show that the eigenvalues (anomalous dimensions) of the new, canonically invariant, evolution kernel coincide with the so-called parity respecting anomalous dimensions. We develop an efficient method that allows one to restore an invariant kernel from the corresponding anomalous dimensions. As an example, the explicit expressions for NNLO invariant kernels for the twist two flavor-nonsinglet operators in QCD and for the planar part of the universal anomalous dimension in $ N=4$ SYM are presented.

hep-ph↗
arXiv2024

Two-loop coefficient functions in deeply virtual Compton scattering: flavor-singlet axial-vector and transversity case

We calculate the two-loop flavor-singlet axial-vector and gluon transversity coefficient functions for deeply virtual Compton scattering in QCD. We observe interesting properties regarding the transcendentality of the transversity coefficient function. Our results complete the calculation of the full next-to-next-to-leading order coefficient function in deeply virtual Compton scattering. Numerically, the two-loop corrections in the axial-vector and transversity channel are comparable to their vector counterpart at moderate skewness parameter ξ and hence indispensable for analyzing the upcoming high-precision data from the Electron-Ion Collider.

hep-ph↗
arXiv2023

Renormalization-Group Evolution for the Bottom-Meson Soft Function

We determine for the first time the renormalization-group (RG) evolution equation for the $B$-meson soft function dictating the non-perturbative strong interaction dynamics of the long-distance penguin contributions to the exclusive $b \to q \ell^{+} \ell^{-}$ and $b \to q γ$ decays. The distinctive feature of the ultraviolet renormalization of this fundamental distribution amplitude consists in the novel pattern of mixing positive into negative support for an arbitrary initial condition. The exact solution to this integro-differential RG evolution equation of the bottom-meson soft function is then derived with the Laplace transform technique, allowing for the model-independent extraction of the desired asymptotic behaviour at large/small partonic momenta.

hep-ph↗
arXiv2023

Connecting Euclidean to light-cone correlations: From flavor nonsinglet in forward kinematics to flavor singlet in non-forward kinematics

We present a unified framework for the perturbative factorization connecting Euclidean correlations to light-cone correlations. Starting from nonlocal quark and gluon bilinear correlators, we derive the relevant hard-matching kernel up to the next-to-leading-order, both for the flavor singlet and non-singlet combinations, in non-forward and forward kinematics, and in coordinate and momentum space. The results for the generalized distribution functions (GPDs), parton distribution functions (PDFs), and distribution amplitudes (DAs) are obtained by choosing appropriate kinematics. The renormalization and matching are done in a state-of-the-art scheme. We also clarify some issues raised on the perturbative matching of GPDs in the literature. Our results provide a complete manual for extracting all leading-twist GPDs, PDFs as well as DAs from lattice simulations of Euclidean correlations in a state-of-the-art strategy, either in coordinate or in momentum space factorization approach.

hep-ph↗
arXiv2023

Distributed Sparse Regression via Penalization

We study sparse linear regression over a network of agents, modeled as an undirected graph (with no centralized node). The estimation problem is formulated as the minimization of the sum of the local LASSO loss functions plus a quadratic penalty of the consensus constraint -- the latter being instrumental to obtain distributed solution methods. While penalty-based consensus methods have been extensively studied in the optimization literature, their statistical and computational guarantees in the high dimensional setting remain unclear. This work provides an answer to this open problem. Our contribution is two-fold. First, we establish statistical consistency of the estimator: under a suitable choice of the penalty parameter, the optimal solution of the penalized problem achieves near optimal minimax rate $\mathcal{O}(s \log d/N)$ in $\ell_2$-loss, where $s$ is the sparsity value, $d$ is the ambient dimension, and $N$ is the total sample size in the network -- this matches centralized sample rates. Second, we show that the proximal-gradient algorithm applied to the penalized problem, which naturally leads to distributed implementations, converges linearly up to a tolerance of the order of the centralized statistical error -- the rate scales as $\mathcal{O}(d)$, revealing an unavoidable speed-accuracy dilemma.Numerical results demonstrate the tightness of the derived sample rate and convergence rate scalings.

cs.LG↗
arXiv2023

Gluon Transverse-Momentum-Dependent Distributions from Large-Momentum Effective Theory

We demonstrate that gluon transverse-momentum-dependent parton distribution functions (TMDPDFs) can be extracted from lattice calculations of appropriate Euclidean correlations in large-momentum effective theory (LaMET). Based on perturbative calculations of gluon unpolarized and helicity TMDPDFs, we present a matching formula connecting them and their LaMET counterparts, where the latter are renormalized in a scheme facilitating lattice calculations and converted to the $\overline{\rm MS}$ scheme. The hard matching kernel is given up to one-loop level. We also show that the perturbative result is independent of the prescription used for the pinch-pole singularity in the relevant correlations. Our results offer a guidance for the extraction of gluon TMDPDFs from lattice simulations, and have the potential to greatly facilitate perturbative calculations of the hard matching kernel.

hep-ph↗