The paper proves barriers to approximating functions with small weights and depth in neural networks.
problem Proving barriers to approximating functions with constant depth neural networks.
method Reduction to open problems and natural-proof barriers in circuit complexity, and a new approach to polynomially-bounded functions.
result There are fundamental barriers to proving results beyond depth 4 for constant-depth neural networks.
The study counts periodic orbits on smooth manifolds, adding ghost orbits for completeness.
problem Counting periodic orbits of vector fields on smooth closed manifolds.
method Enlarging the space of orbits to include ghost orbits, defining weight functions, and showing constancy under deformation.
result The weight function remains constant as the vector field moves and Γ deforms. Establishes convexity and coercivity of K-energy functional for complex tori.
problem Convexity and coercivity of K-energy functional for complex tori.
method Geodesics in finite energy space, cone angle perturbations, stability of coercivity.
result Openness of coercivity under cone angle perturbations and existence of cscK cone metrics.
New insights into Kähler Ricci solitons and Calabi-Yau cones.
problem Understanding Kähler Ricci solitons and their relationship to Calabi-Yau cones.
method Analyzing the canonical cone of Fano manifolds and using openness of weight functions.
result The canonical cone of a product of a smooth Fano manifold and a complex projective space is a Calabi-Yau cone under certain conditions.
A classical result due to Blaschke states that for every analytic self-map f of the open unit disk of the complex plane there exists a Blaschke product B such that the zero sets of f and B agree. In this paper we show that there is an analogue statement for critical sets, i.e. for every analytic self-map f of…
Neural networks with learned biases can approximate any function.
problem Whether neural networks with only learned biases can approximate any continuous function.
method Theoretical and numerical analysis of random weights and learned biases in neural networks.
result Feedforward and recurrent neural networks with random weights can approximate any continuous function and dynamical systems.
In the paper arXiv:1411.4887 [math.AP] it is shown that the set of Riemannian metrics which do not admit global limiting Carleman weights is open and dense, by studying the conformally invariant Weyl and Cotton tensors. In the paper arXiv:1011.2507 [math.DG] it is shown that the set of Riemannian metrics which do not a…
KANs replace fixed MLP weights with learnable edge functions, improving accuracy and interpretability.
problem Lack of interpretability and scalability in MLPs.
method KANs use learnable activation functions on edges instead of fixed weights, replacing weights with spline functions.
result KANs outperform MLPs in accuracy and interpretability with smaller models.
A new approach optimizes weights in DLP for better risk-adjusted performance.
problem Optimizing time-varying weights in Double Linear Policy (DLP) for better risk-adjusted performance.
method Stochastic Model Predictive Control (SMPC) framework to maximize risk-adjusted returns while enforcing constraints.
result Empirical results show improved risk-adjusted performance and drawdown control.
RWR converges to global optimum in certain settings.
problem Proving convergence of RWR to optimal policy.
method Iterative learning with return-weighted log-likelihood.
result RWR converges to global optimum under certain conditions.
Paper proposes a robust LPR method using similarity kernels.
problem Outliers and high-leverage points affect traditional LPR's accuracy.
method Integrates predictor and response variables in weighting mechanism using a conditional density kernel.
result Lower empirical bias compared to iterative robust LOWESS.
Proposes a method to estimate causal effects of continuous treatments using instrumental variables.
problem Estimating causal effects of continuous treatments in the presence of unmeasured confounders.
method Introduces a novel framework using instrumental variables and a uniform regular weighting function to identify and estimate average dose-response functions.
result Establishes the asymptotic properties of the proposed methods for estimating average dose-response functions.
The capitalization-weighted total relative variation ∑i=1d∫0⋅μi(t)d⟨logμi⟩(t) in an equity market consisting of a fixed number d of assets with capitalization weights μi(⋅) is an observable and nondecreasing function of time. If this observable of the market …
The paper proves Calabi-Bernstein type results for minimal and maximal surfaces in 3D and 3D-L spacetime.
problem Characterizing minimal and maximal surfaces in 3D and 3D-L spacetime.
method Analyzing surfaces with specific properties and using geometric and functional methods.
result Calabi-Bernstein type results for critical points of a weighted area functional in R3 and L3. New method prevents deep learning forgetting past by remembering key examples.
problem Catastrophic forgetting in continual learning.
method Functional regularisation using Gaussian Process formulation.
result Achieves state-of-the-art performance on benchmarks.
Let G be a torus acting linearly on a complex vector space M, and let X be the list of weights of G in M. We determine the equivariant K-theory of the open subset of M consisting of points with finite stabilizers. We identify it to the space DM(X) of functions on the lattice of weights of G, satisfying the cocircuit di…
Improved text summarization using belief propagation on weighted bipartite graphs.
problem Text summarization from a graph theory perspective.
method Generalized belief propagation algorithm for weighted bipartite graphs.
result Our algorithm outperforms greedy methods in text summarization tasks.
We present a set of high-probability inequalities that control the concentration of weighted averages of multiple (possibly uncountably many) simultaneously evolving and interdependent martingales. Our results extend the PAC-Bayesian analysis in learning theory from the i.i.d. setting to martingales opening the way for…
Uniformises Kähler surfaces with positive curvature to complex plane.
problem Uniformisation of complete Kähler surfaces with positive sectional curvature.
method New approach using uniformly Lipschitz plurisubharmonic weight functions and weighted holomorphic functions.
result Proves any complete non-compact Kähler surface with positive sectional curvature is biholomorphic to C^2.
Study fine Pólya-Szegő inequalities in metric spaces with applications.
problem Fine Pólya-Szegő rearrangement inequalities in metric spaces.
method Theory of Sobolev and BV functions, synthetic Ricci bounds, isoperimetric inequality.
result New geometric and functional inequalities under Ricci lower bounds.
This paper solves a variation of the isoperimetric problem in higher dimensions.
problem Minimizing a weighted perimeter functional with given half-space volumes.
method Introduced a weighted perimeter functional with three weights.
result Characterized two types of minimizers made of spherical domes.
Efficient WKNN-Shapley computation improves data valuation accuracy.
problem Efficient computation of Data Shapley for WKNN algorithm.
method Reframed WKNN-Shapley as a counting problem, introduced quadratic-time algorithm.
result Quadratic-time WKNN-Shapley computation, improving from O(NK). We organize the quantum hyperbolic invariants (QHI) of 3-manifolds into sequences of rational functions indexed by the odd integers N≥3 and defined on moduli spaces of geometric structures refining the character varieties. In the case of one-cusped hyperbolic 3-manifolds M we generalize the QHI and get rati…
Paper proves a new isoperimetric inequality for Steklov eigenvalues.
problem Finding a new isoperimetric inequality for Steklov eigenvalues.
method Proving a Brock-type inequality under specific conditions.
result Extension of Brock's classical result to Witten-Laplacian.
Fix a smooth closed manifold M. Let RM denote the space of all pairs (g,L) such that g is a C3 Riemannian metric on M and the real number L is not the length of any closed g-geodesics. A locally constant geodesic count function πM:RM→Z is constructed. For this purpose, the weight of com…
Let Ω be an open half-space or slab in Rn+1 endowed with a perturbation of the Gaussian measure of the form f(p):=exp(ω(p)−c∣p∣2), where c>0 and ω is a smooth concave function depending only on the signed distance from the linear hyperplane parallel to ∂Ω. In this work we follow a varia…
ModHiFi identifies critical components for model modification without gradients or loss function.
problem Modifying open weight models without access to training data or loss function.
method Theoretical analysis of Lipschitz-continuous networks, Subset Fidelity metric, and ModHiFi algorithm.
result ModHiFi-P and ModHiFi-U achieve significant performance improvements in model pruning and unlearning.
This paper classifies strongly nilpotent special multi-flags and their Goursat counterparts.
problem Local classification of strongly nilpotent special multi-flags and Goursat distributions.
method Study of special multi-flags in homogeneous case, focusing on their weights.
result Strongly nilpotent germs of multiflags from different singularity classes are pairwise inequivalent.
We study some basic analytic questions related to differential operators on Lie manifolds, which are manifolds whose large scale geometry can be described by a a Lie algebra of vector fields on a compactification. We extend to Lie manifolds several classical results on Sobolev spaces, elliptic regularity, and mapping p…
In this work, we extend the SchNet architecture by using weighted skip connections to assemble the final representation. This enables us to study the relative importance of each interaction block for property prediction. We demonstrate on both the QM9 and MD17 dataset that their relative weighting depends strongly on t…
PCA reveals a market factor in S&P500 implied volatilities.
problem Constructing factor models from implied volatility data.
method PCA on implied volatility tensor structure.
result An OI and Vega-weighted index is a significant factor.
Open AI models affect bond yields differently than closed ones.
problem Understanding how market reactions to AI releases impact bond yields.
method Analyzed US bond yields before and after the release of open and closed AI models.
result Open AI models shift bond yields in the opposite direction of closed models.
First example of open manifold with positive Ricci curvature and non-proper Busemann function.
problem Counterexample to Busemann function properness in open manifolds with nonnegative Ricci curvature.
method Provided an open manifold with positive Ricci curvature and non-proper Busemann function.
result First example of open manifold with positive Ricci curvature and non-proper Busemann function.
Sharp Steklov eigenvalue estimates for differential forms on manifolds.
problem Estimating the first positive eigenvalue of the Steklov eigenvalue problem for differential forms.
method Established a weighted Reilly formula for differential forms and applied it to geometric conditions.
result Sharp lower bound for the first positive eigenvalue of the Steklov eigenvalue problem on differential forms.
This paper studies optimal approximation factors in misspecified off-policy RL, identifying key factors under various settings.
problem Understanding optimal approximation factors in misspecified off-policy value function estimation.
method Examined various settings including weighted L2-norm, L∞ norm, state aliasing, and state coverage. result Established optimal asymptotic approximation factors for different norms and identified two instance-dependent factors for L2(μ) norm. The paper studies Finsler manifolds with a new curvature concept.
problem Understanding Finsler manifolds with positive weighted flag curvature.
method Introducing a new curvature concept based on the flag curvature and a non-Riemannian quantity, T-curvature.
result Positive weighted flag curvature implies the manifold is diffeomorphic to Euclidean space.
We show theoretical similarities between the Least Squares Support Vector Regression (LS-SVR) model with a Radial Basis Functions (RBF) kernel and maximum a posteriori (MAP) inference on Bayesian RBF networks with a specific Gaussian prior on the regression weights. Although previous works have pointed out similar expr…
The paper sparsifies networks by finding efficient paths in their functional space.
problem Sparsifying neural networks to improve performance and efficiency.
method The authors use the geometry of weight spaces and functional manifolds to find efficient paths (geodesics) in the functional space of neural networks.
result The proposed framework can sparsify networks and improve performance on various tasks.
The paper discusses rigidity results for inequalities on weighted Riemannian manifolds.
problem Rigidity of inequalities on weighted Riemannian manifolds.
method Theorems of rigidity on curvature and measure for the Borell-Brascamp-Lieb inequality, generalizing a theorem by Balogh and Kristály.
result A generalization of the curvature rigidity theorem to the weighted setting.
Polynomial growth bounds for eigenfunctions on non-compact spaces.
problem Growth of eigenfunctions on non-compact spaces with Gaussian weight.
method Analyzing non-compact manifolds with Gaussian weight and drift Laplacian.
result Showed same polynomial growth bounds as Euclidean space for general tensors.
We study the Yamabe problem on open manifolds of bounded geometry and show that under suitable assumptions there exist Yamabe metrics, i.e. conformal metrics of constant scalar curvature. For that, we use weighted Sobolev embeddings.
Optimizes sample weights for representative data averages.
problem Achieving sample averages close to prescribed values.
method Formulates as an optimization problem, often convex and efficiently solvable.
result Heuristic methods based on convex optimization perform well.
Deep equilibrium models converge globally without explicit computation.
problem Global convergence of deep learning models with implicit layers.
method Analysis of gradient dynamics and proof of convergence rate.
result Deep equilibrium models converge to global optimum at a linear rate.
We prove some old and new isoperimetric inequalities with the best constant using the ABP method applied to an appropriate linear Neumann problem. More precisely, we obtain a new family of sharp isoperimetric inequalities with weights (also called densities) in open convex cones of Rn. Our result applies to…
New framework for data-driven hyperparameter tuning with structured loss.
problem Statistical foundations for multi-dimensional hyperparameter tuning remain limited.
method General framework using real algebraic geometry for semi-algebraic function classes.
result First general guarantees for multi-dimensional hyperparameter tuning.
Optimization of Binarized Neural Networks (BNNs) currently relies on real-valued latent weights to accumulate small update steps. In this paper, we argue that these latent weights cannot be treated analogously to weights in real-valued networks. Instead their main role is to provide inertia during training. We interpre…
wd1 improves reasoning in dLLMs by optimizing policies without policy ratios.
problem Improving reasoning in diffusion-based large language models through RL.
method wd1: ratio-free policy optimization using weighted log-likelihood.
result wd1 outperforms diffusion-based GRPO while requiring lower computational cost.
Density estimation is a versatile technique underlying many data mining tasks and techniques,ranging from exploration and presentation of static data, to probabilistic classification, or identifying changes or irregularities in streaming data. With the pervasiveness of embedded systems and digitisation, this latter typ…