Training Gaussian processes (GPs) at large scale is computationally challenging because evaluating the log-marginal likelihood and its gradients involves large, dense kernel matrices. We develop a scalable low-rank GP training approach that combines AnchorNet landmark selection with a fully independent training conditional (FITC) correction. The resulting objective and its analytic gradients can be evaluated using low-rank factors, diagonal quantities, and small dense matrices, without forming the full kernel matrix or its derivatives. The complete training procedure is implemented in single precision and evaluated on nine large-scale regression datasets. Across these problems, the method reaches the reference predictive accuracy while substantially reducing training time, although the required approximation rank varies across datasets. We also study the numerical behavior of the full-kernel predictive solve and show that single precision can become limiting for ill-conditioned problems. Finally, we investigate further reducing selected matrix operations to fp16 or TF32. These lower-precision variants provide only modest additional speedups and can become unreliable when the reduced system is poorly conditioned.
The Adam optimizer is widely used to train neural networks with highly nonlinear and nonconvex objective functions. Remarkably, Adam often drives the empirical training loss nearly to zero. This phenomenon has been partially explained by neural tangent kernel (NTK) analyses of gradient descent (GD) and stochastic gradient descent (SGD). However, analyzing Adam presents additional challenges. Its first-moment momentum couples stochastic gradients across iterations, while its adaptive second-moment preconditioner depends on the same stochastic gradient used in the update. In this paper, we establish linear convergence guarantees for Adam in training sufficiently wide two-layer neural networks with either full-batch or minibatch gradients. For full-batch Adam, we construct a Lyapunov function to control the effect of historical momentum. For minibatch Adam, our analysis builds on an exact virtual-iterate representation, a conditional analysis of the dependence between stochastic gradients and adaptive preconditioners, and uniform concentration bounds for the second-moment estimates. We prove geometric decay of the empirical loss for full-batch Adam and geometric decay in restricted expectation on a high-probability event for minibatch Adam. Beyond regression, we extend our convergence analysis to physics-informed neural networks (PINNs) for solving the Poisson equation, where differential operators and separate sampling of interior and boundary points introduce additional challenges. We establish analogous global convergence guarantees for both deterministic and stochastic Adam under explicit conditions on network width and Adam's parameters, characterizing the effects of minibatch size on convergence. These results help bridge the gap between Adam's empirical success and its theoretical understanding, providing sharper convergence guarantees for PINNs than existing analyses.
We study the learning of homogenized constitutive laws for inelastic heterogeneous materials, aiming to replace costly concurrent unit-cell simulations with surrogates that generalize across loading histories and microstructures. We focus on the recurrent neural operator framework, motivated by the explicit form of homogenized Kelvin--Voigt linear viscoelasticity. In this framework, internal variables enable a Markovian approximation of loading-history dependence, and neural operators represent the microstructure-dependent constitutive response. For periodic Kelvin--Voigt viscoelasticity, we prove a universal approximation theorem showing that the model can approximate the homogenized constitutive law to any prescribed accuracy, uniformly in time and over a wide set of admissible strain trajectories and microstructural property fields, in two and three dimensions. This comprises a significant extension of the existing, somewhat limited, one-dimensional theory that uses explicit solutions for piecewise constant materials. Instead, in two and three dimensions, we adopt a more versatile approximation based on the spectral representation of the memory kernel that arises from homogenization. This also enables us to give an explicit bound on the internal-variable dimension, sufficient for approximation, exhibiting logarithmic growth in the inverse relative stress error and in material contrast. Numerical experiments on viscoelasticity and crystal plasticity complement the theory, illustrating the roles of internal-variable dimension and sample complexity in learning homogenized responses from unit-cell data. Theoretical results are formally verified in Lean 4.
Stochastic first-order methods use sampled gradients to reduce per-iteration costs, but estimation errors can slow convergence and, in some settings, cause divergence. To improve gradient accuracy while retaining acceleration, we develop scalar and diagonal versions of VR-Adam-SHANG for smooth stochastic convex optimization. The methods combine STORM-type recursive estimation, Adam-style preconditioning, and SHANG's accelerated interpolation and correction, using at most two stochastic gradient evaluations per iteration without full-gradient refreshes. Under unbiased sampling, bounded variance, and mean-square smoothness of gradient noise, polynomial steps with prescribed initialization yield $O(1/K)$ mean-square gradient-estimation error and expected objective-gap bounds combining $O(1/K^2)$ initial-energy decay with an $O(1/\sqrt K)$ stochastic term after $K$ iterations. These guarantees require neither monotonicity of the preconditioner nor a uniform positive lower bound on its eigenvalues. The analysis also establishes polynomial-step convergence of projected nonrecursive Adam-SHANG-s, filling a gap in its original theory. Experiments compare the methods at matched sample-gradient budgets. In every tested setting, at least one of the two versions achieves the lowest mean terminal objective gap among all compared methods.
AI agents are increasingly capable of discovering new mathematical results, yet their reasoning and generated proofs can be difficult to understand and verify. We introduce an interpretable framework for AI-guided mathematical discovery, focused on improving quantitative bounds on analytic constants. Our key insight is that existing proofs often contain slack in intermediate lemmas, which can be tightened without reconstructing the entire argument. To exploit this structure, we represent proofs as partially-formalized Lean blueprints: human-interpretable dependency graphs of definitions, lemmas, and theorems. An AI agent then iteratively refines the Lean code while preserving the blueprint's dependency structure, allowing local improvements to automatically propagate to a verified final bound. This interpretable structure allows humans to inspect the agent's refinements and understand how local improvements propagate to the final theorem. For Grothendieck's constant ($\mathcal{K}_G$), we obtain $$ \mathcal{K}_G \leq \frac{\pi}{2\log(1+\sqrt{2})} - 10^{-17}, $$ an explicit numerical improvement over Krivine's 1977 bound. For Korenblum's constant ($\mathcal{K}_K$), we obtain $$ \mathcal{K}_K \geq 0.356565, $$ improving Wang's 2025 bound of $0.3554$. Our experiments demonstrate the potential of both partial formalization and iterative agentic refinement for interpretable mathematical discovery.
Neural networks trained by gradient-based methods learn the low-frequency content of a target function faster than its high-frequency content. This spectral bias is well documented, but it is much less clear which architectural choices mitigate it and which cannot. We study the question for shallow ReLU models linear in their trainable parameters, where each mode is learned at a rate given by a Gram-matrix eigenvalue, and for a general symmetric bilinear form $a(\cdot,\cdot)$, so that least-squares regression ($a=$ the $L^2$ inner product) and variational or physics-informed losses ($a=$ the $H^1$ energy form) are two instances of one analysis. Within this framework we propose gated local ReLU dictionaries, obtained by multiplying each ReLU feature by a hat partition-of-unity weight, in the spirit of partition-of-unity finite elements and overlapping Schwarz methods. The resulting Gram matrices are block-banded for any local bilinear form, with a block-Toeplitz interior whose matrix-valued symbol governs the spectrum. The two forms then behave very differently. For $L^2$ regression, the symbol is bounded away from zero, the ratio is uniform in the number of windows, and the measured spread of frequency-dependent learning rates falls from $1.9\times10^{5}$ to $4.5$ at matched model size. For the $H^1$ stiffness matrix, the symbol vanishes at zero frequency: gating leaves the $\Theta(N^2)$ conditioning intact and inverts the frequency ordering instead of removing the bias. A preconditioner built from the same interior stencil will fix the spectral bias, showing that architecture alone is not enough. Experiments on $1$D regression and Poisson problems confirm the dichotomy, and the regression effect persists when the hidden-layer parameters are trained as well.
We present a novel GPU-accelerated global solver for constrained nonlinear programming (NLP) inspired by the efficient linear bound propagation framework in neural network (NN) verification. Existing work on NN verification, a problem that can be cast as feasibility detection for a nonlinear objective, demonstrated orders-of-magnitude speedups with the linear bound propagation-based framework when compared to traditional solvers. Extending this paradigm to global nonlinear programming requires addressing many challenges: a global constrained NLP solver must effectively exploit all, possibly unstructured, nonlinear constraints to improve the objective, whereas NN verification typically handles simple input box constraints over a well-structured NN and does not directly optimize an objective function. We address these challenges by fully exploiting the linear bounds produced by bound propagation: these linear bounds can be viewed as relaxations of nonlinear constraints and used to provide lower bounds, check infeasibility, and guide the search for a primal solution. In addition, we propose tighter linear relaxations for bilinear, quotient, and other commonly used nonlinear functions in NLP problems, and a projected augmented Lagrangian method tightly coupled to our dual solving procedure to produce primal solutions. Our method solves 421 of 505 bounded and continuous NLP problems in the GAMS and MINLPLib benchmarks under a 180-second limit, more than each of the six global solvers we compare with, including Gurobi and BARON (commercial), and SCIP (open-source). Sixteen of these problems are certified by none of the six global solvers; all of them contain exponential, logarithmic, or trigonometric terms, which are often challenging for traditional approaches. Project webpage is at https://verified-intelligence.github.io/GEAR.
We introduce P-IMLA, a preconditioned implicit-midpoint Langevin sampler for high-dimensional log-concave targets with non-smooth regularization. The obstruction is that the large steps enabled by matrix preconditioning are precisely where preconditioned Euler-Maruyama inflates stationary variance. Implicit midpoint removes this surplus via a Cayley-transform identity, making P-IMLA Gaussian-exact at any step size. Beyond Gaussians, whitening transfers the sharp IMLA contraction rate to $\kappa_{\mathrm{eff}}$, and backward-error analysis gives drift-only rather than Euler-type diffusion bias under explicit smoothness assumptions. An $M$-norm Moreau envelope yields a proximal non-smooth variant with a three-term error budget. Controlled Gaussian and TV-regularized imaging experiments confirm the predicted separation: the unpreconditioned midpoint scheme retains long transients as $\kappa_f$ grows, whereas P-IMLA remains $\kappa_{\mathrm{eff}}$-governed and near variance-exact.
Stationary tail computation for high-dimensional reflected Brownian motions (RBMs) remains computationally challenging. Building on NN4MGF's shared-coordinate basic-adjoint-relationship (BAR) framework, we develop Holomorphic Cauchy Networks (HCNs). Native complex-valued rational Cauchy subnetworks enforce holomorphicity on pole-free domains, removing sampled Cauchy-Riemann penalties and their input-derivative graphs. Exact origin anchoring and boundary-coordinate exclusion enforce structural identities, while anchored interactions represent dependent transforms. Under holomorphic-log assumptions, we establish simultaneous value and first-derivative approximation for the constrained architectures and a mixed-derivative lower bound for coordinate-only representations under nonzero cross-covariance. Closed-form real-axis derivatives and sequential backpropagation further control memory. On the same NVIDIA H100 NVL, the tested 30D HCN configuration uses approximately tenfold less peak allocated memory and has 9.7-fold lower mean update time than NN4MGF; extrapolation to the respective scheduled update counts gives a projected full-schedule update-time ratio of 58.2. With 64 million sampled base inputs per high-dimensional run, HCN reaches 50 dimensions on a laptop GPU with 6.367% mean relative error over thresholds 1 through 8. Degree-matched comparisons yield lower reported mean relative errors over the primary evaluation ranges, including 1.422% versus 6.684% on the 2D Harrison non-product benchmark. On a 10D correlated RBM benchmark, HCN achieves 3.829% mean relative error over thresholds 1 through 8 against a simulation reference, compared with 19.386% for an independent-marginal baseline.
Neural surrogate solvers of partial differential equations (PDEs) promise dramatic speedups over numerical methods, especially in scenarios requiring many solves. However, current accuracy-based evaluations do not fully consider two central issues: (1) neural solvers incur substantial up-front costs for data generation, training, and tuning; and (2) classical solvers can also generate low-fidelity solutions at a sufficiently low simulation cost. To explicitly account for these realities and fully incorporate end-to-end costs, we propose an evaluation framework centered on breakeven complexity, a metric that counts the forward solves before a learned solver is cost-effective relative to an error-equivalent traditional solver. To evaluate this measure, we apply scaling laws to determine how much training budget to allocate to data generation and discuss how to achieve smooth error-matching in diverse settings. We evaluate the breakeven complexity of multiple neural PDE solvers on three PDEs on 2D periodic domains from APEBench and a novel benchmark of flows past multiple obstacles generated by the GPU-native PyFR code. Among other findings, our results suggest that neural PDE solvers become more effective as problems get harder in terms of cost, dimension, rollout, physics regime (e.g. higher Reynolds number), etc.
In this paper, we introduce INEUS, a meshfree iterative neural solver for partial integro-differential equations (PIDEs). The method replaces the explicit evaluation of nonlocal jump integrals with single-jump sampling and reformulates PIDE solving as a sequence of recursive regression problems. Like Physics-Informed Neural Networks (PINNs), INEUS learns global solutions over the entire space-time domain, yet it offers a more efficient treatment of nonlocal terms and avoids the computationally expensive differentiation of full PIDE residuals. These features make INEUS particularly well suited for high-dimensional PDEs and PIDEs. Supported by a contraction-based convergence proof for linear PIDEs, our numerical experiments show that INEUS delivers accurate and scalable solutions for various high-dimensional linear and nonlinear examples.
Generative compressed sensing uses the range of a pretrained generator as a nonlinear model for recovering structured signals from limited measurements. We study a conditional version of this problem for image recovery from subsampled Fourier measurements using prompt-conditioned generative models. Our framework separates two roles of conditioning: the prompt used to design the sampling distribution and the prompt used to define the recovery model. For ReLU and Lipschitz conditional generators, we prove stable recovery bounds showing that prompt-matched Christoffel sampling retains the same Christoffel complexity constant as existing near-optimal generative compressed sensing theory, while prompt mismatch incurs an explicit compatibility penalty. Experiments with Stable Diffusion show that prompts meaningfully reshape Christoffel sampling distributions and influence image recovery. Overall, our results suggest treating prompts as design variables for sensing, approximation, and recovery, opening new directions for the practical use of conditional generative models in compressed sensing, where conditioning, sampling, and optimization must be considered jointly.
Training implicit neural representations (INRs) to capture fine-scale details typically relies on iterative backpropagation and is often hindered by spectral bias when the target exhibits highly non-uniform frequency content. We propose ELM-INR, a backpropagation-free INR that decomposes the domain into overlapping subdomains and fits each local problem using an Extreme Learning Machine (ELM) in closed form, replacing iterative optimization with stable linear least-squares solutions. This design yields fast and numerically robust reconstruction by combining local predictors through a partition of unity. To understand where approximation becomes difficult under fixed local capacity, we analyze the method from a spectral Barron norm perspective, which reveals that global reconstruction error is dominated by regions with high spectral complexity. Building on this insight, we introduce BEAM, an adaptive mesh refinement strategy that balances spectral complexity across subdomains to improve reconstruction quality in capacity-constrained regimes.
We study fixed-policy evaluation for finite Markov chains that may be reducible and periodic. Classical evaluation methods with gain and bias decomposition are not always diagnostic: the gain records only invariant Ces\`aro averages, while persistent phase-dependent behavior is absorbed into the bias together with genuinely transient effects. We identify the real peripheral invariant subspace $\mathcal{K}(P)$ of the transition matrix $P$ as the source of this ambiguity. Quotienting by $\mathcal{K}(P)$ is the minimal exact quotient that removes all non-decaying modes and makes the remaining dynamics strictly stable. After choosing a gauge projection $\Pi$ with kernel $\mathcal{K}(P)$, the reward admits a unique decomposition $r = g_\Pi^\star + (I-P)v_\Pi^\star$, where $g_\Pi^\star$ is a persistent regime profile and $v_\Pi^\star$ is a gauge-fixed transient component. An exact comparison with classical normalized gain and bias shows that the new pair reallocates the same information into a persistent profile and a gauge-fixed representative of the transient quotient. This decomposition reconstructs finite-horizon returns, recovers statewise average reward, admits a transient-cost interpretation, and yields a stable estimator under a generative model.
Physics-Informed Neural Networks (PINNs) often struggle to approximate solutions with sharp gradients due to optimization difficulties and spectral bias. Motivated by the principle of gradient equidistribution from the stretching approach in grid generation, which redistributes solution gradients to reduce functional complexity, we propose Coordinate Transformation PINNs (CTPINNs), which incorporate learnable coordinate transformations to map the physical domain into a computational domain where the physical solutions become approximately affine, making them easier for neural networks to learn. We propose two constructions of the transformation: an explicit construction based on Majorants and an implicit construction based on invertable neural networks. Experimentally, the explicit construction can improve accuracy for PDEs with available explicit coordinate transformations, and the implicit construction can be combined with other advanced PINN models as an efficient plug-in module to improve performance across a range of challenging PDE benchmarks.
We prove that the set $\mathcal{N}_N$ of ReLU networks with one hidden layer and at most $N\in\mathbb N$ neurons is weakly closed in $W^{1,p}(\Omega)$, for a bounded connected open set $\Omega\subset\mathbb R^d$. Consequently, every coercive, weakly lower semicontinuous energy on this space attains its minimum over $\mathcal{N}_N$. This covers the Deep Ritz method with convex integrands, Sobolev training and Lipschitz learning. Moreover, as the weight decay parameter tends to zero, minimizers of the regularized problem converge, up to subsequences, to minimizers with minimal parameter norm. We also prove that the set of ReLU networks with two hidden layers of bounded widths is not closed in $W^{1,p}(\Omega)$ or in $C(\overline\Omega)$. This disproves a conjecture of Petersen, Raslan and Voigtlaender.
Thermal simulation is becoming increasingly critical in modern IC design and manufacturing. Feynman--Kac random walk methods can estimate localized temperatures without solving the global field, but in practical settings without Dirichlet boundaries they require very long paths to control the truncation residual. This paper presents FasterRW, a continuation-value framework for accelerating Feynman--Kac thermal random walks. We prove a stopping-time residual identity showing that the expected tail after truncation equals the current attenuation weight multiplied by the temperature at the stopping location. This identity enables a prior-corrected single-point estimator: a cheap, noisy prior replaces the unknown continuation value, making the truncation bias scale with prior error rather than absolute temperature and yielding an error-controlled threshold-selection rule. For multi-point queries, FasterRW further converts cross-query pass-through tails into pseudo-samples and refines the resulting observations in prior-error coordinates through kriging. Compared with prior state-of-the-art methods, FasterRW achieves up to $28\times$ acceleration while maintaining accuracy. Our code is open-sourced at https://github.com/ShiningSord/FastRW.
Phase-field models are widely used to simulate microstructure evolution but their numerical solution remains computationally demanding. Neural operator surrogates provide a promising alternative, yet existing approaches are data-driven, requiring large datasets and exhibiting limited robustness when extrapolating to unseen configurations. We introduce DeepRitzSplit, an unsupervised neural operator framework for gradient-flow systems based on a variational formulation of energy-stable splitting schemes. It learns the time evolution semigroup associated with a convex-concave free-energy decomposition by minimizing the underlying variational problem at each time step. It is designed to inherit the dissipative structure of the underlying gradient flow without requiring trajectory datasets. We further introduce a Reaction-Diffusion Neural Operator (RDNO) architecture motivated by splitting schemes, with separate reaction and diffusion components to improve training efficiency and interpretability. We assess the approach on the Allen-Cahn equation and apply it to a phase-field model of anisotropic dendritic growth during solidification. In the Allen-Cahn benchmark, DeepRitzSplit shows better generalization than the supervised baseline on the out-of-distribution configurations tested, using 180 training configurations. In dendritic growth, the method captures the overall phase morphology and dendrite tip velocity well, while the tip radius is more sensitive to the training strategy. Refinement based on the residual of the splitting scheme markedly improves this second-order morphological quantity. The trained operators retain good predictive capabilities on configurations substantially different from the training set. These results demonstrate the potential of variationally trained neural operators as physically informed surrogates for accelerated microstructure simulations.
Physics-informed neural networks (PINNs) often suffer from imbalanced optimization of competing loss components, particularly when approximating solutions with high-frequency or multiscale features. Although existing balancing strategies have proven effective in alleviating this difficulty, the mechanisms governing the evolution of individual task contributions to Adam's parameter updates remain insufficiently understood. We introduce task-wise indicators to characterize this evolution and identify three distinct training regimes: smooth variation, intermittent spikes, and persistent oscillations. Focusing on the early smooth regime, we combine discrete-time analysis with a continuous-time singular perturbation framework under the full-batch setting and the parameter regime $(1-\beta_2)/(1-\beta_1)\ll1$. A first-order approximation of the locally attracting slow manifold reveals two factors governing the step-to-step redistribution of task contributions: curvature-related alignment disparities and differences in the coordinatewise distributions of preconditioned task gradients. Both factors involve Adam's shared second-moment estimate. Inspired by AdaTask, we propose Gradient-Modulated Adam (GMAdam), which modulates incoming task gradients using task-specific second-moment estimates. Numerical experiments on high-frequency Poisson and wave equations, the Allen-Cahn equation, and two-dimensional lid-driven cavity flow ($Re=100,400$) demonstrate consistent improvements in predictive accuracy over AdaTask at comparable computational cost.
Discovering continuous symmetries directly from differential-equation data can reveal geometric structure for model reduction and scientific machine learning without symbolic determining equations or a closed-form representation of the governing system. We formulate intrinsic Lie point-symmetry discovery as an operator-theoretic problem on sampled jet-space data. Admissible generators are identified from a sampled determining operator and separated from redundant, solution-dependent, and geometrically trivial directions. The framework combines prolongation, sequential subspace restrictions, and a fixed nonlinear dictionary linear in trainable coefficients. A rank-stabilization preflight test diagnoses systems whose represented intrinsic symmetry algebra does not stabilize under dictionary refinement. On a controlled differential-equation benchmark with an analytically known 11-dimensional represented intrinsic symmetry algebra, the method recovers the complete represented generator set, reproduces its Lie-bracket structure to numerical precision, and approximates a known generator beyond the training domain. Here we show that explicit intrinsic continuous-symmetry generators can be recovered from data obtained from exact or approximate differential systems.