New gradient Ricci solitons found for SU(2) invariants.
problem Exploring gradient Ricci solitons with SU(2) symmetry. method Construction of new solitons using cohomogeneity one group actions.
result 3-parameter families of complete SU(2)-invariant asymptotically conical expanding gradient Ricci solitons. In this paper we show that all conformal metrics to a pseudo-euclidean space invariant under the translation group, and all the conformal metrics product manifold also invariant by translation where F m it is Ricci flat semi-Riemannian manifold, are gradient Ricci almost soliton. We also proved that all conformal metri…
The paper classifies invariant gradient k-Yamabe solitons in pseudo-Euclidean spaces.
problem Characterizing invariant gradient k-Yamabe solitons in pseudo-Euclidean spaces. method Characterization through the action of an (n−1)-dimensional translation group and classification of rotational invariant solutions. result Infinitely many explicit examples of geodesically complete steady gradient k-Yamabe solitons are constructed. This paper explores gradient flows for sampling distributions without normalization constants.
problem Sampling from distributions with unknown normalization constants.
method Gradient flows in the space of probability measures, focusing on Kullback-Leibler divergence, Fisher-Rao metric, and affine invariance.
result Gradient flows derived from Kullback-Leibler divergence do not depend on the normalization constant.
We develop a coordinate-free approach to natural gradient descent for scalable neural networks.
problem First-order optimization methods are sensitive to model parameterization.
method We construct a coordinate-free natural gradient and analyze its invariance properties for K-FAC.
result K-FAC's natural gradient matches the coordinate-free update, maintaining invariance to affine transformations.
This paper concerns local gradient estimates to solutions of general conformally invariant fully nonlinear elliptic equations of second order.
Study expanding gradient Ricci solitons with Euclidean base.
problem Characterize expanding gradient Ricci solitons with specific properties.
method Analyze warped products with Euclidean base and invariant warping functions.
result Derive complete examples of expanding gradient Ricci solitons.
This paper studies gradient flows for sampling using various metrics and their affine invariance.
problem Sampling from probability distributions with unknown normalizations.
method Gradient flows in the space of probability measures, focusing on Kullback-Leibler divergence and affine invariance of metrics.
result Gradient flows of Kullback-Leibler divergence do not depend on the normalization constant, and affine invariance is achieved for certain metrics.
Study proves structure results for homogeneous spaces supporting specific equations.
problem Proving structure results for homogeneous spaces supporting specific equations.
method Analyzing homogeneous spaces with non-constant solutions to two general classes of equations involving the Hessian and an invariant 2-tensor.
result Generalizes rigidity results for gradient Ricci solitons and warped product Einstein metrics.
New steady gradient Ricci solitons found on specific four-manifolds.
problem Finding steady gradient Ricci solitons on specific four-manifolds.
method Center manifolds and topological degree theory.
result New families of complete, SU(2)-invariant steady gradient Ricci solitons constructed. The paper generalizes optimization algorithms using category theory.
problem Optimizing functions in a category-theoretic setting.
method Using the Cartesian reverse derivative to generalize gradient descent and Newton's method.
result Properties of optimization algorithms are preserved in the generalized setting, including invariances and convergence.
Flow on curves in inversive geometry converges to loxodromics.
problem Gradient flow for curve length in inversive geometry.
method Invariant gradient flow for invariant length functional.
result Solutions exist for all time and converge to loxodromic curves.
Adam performs better with equal momentum parameters, revealing a gradient scale invariance principle.
problem Why Adam performs better with β1=β2. method Formalized gradient scale invariance and proved it for Adam with equal β1 and β2. result Adam becomes gradient scale invariant of first order if and only if β1=β2. We consider generalized gradients in the general context of G-structures. They are natural first order differential operators acting on sections of vector bundles associated to irreducible G-representations. We study their geometric properties and show in particular their conformal invariance.
With a f-left-invariant Riemannian metric on a Lie group G, we mean a Riemannian metric which is conformally equivalent to a left-invariant Riemannian metric, with the conformal factor f. In this article, we study the geometry of such metrics and give a necessary and sufficient condition for an f-left-invariant Rie…
The works of Donaldson and Mark make the structure of the Seiberg-Witten invariant of 3-manifolds clear. It corresponds to certain torsion type invariants counting flow lines and closed orbits of a gradient flow of a circle-valued Morse map on a 3-manifold. We study these invariants using the Morse-Novikov theory and H…
Investigates spectral properties of neural networks, showing invariance under certain conditions.
problem Understanding the spectral evolution and invariance in linear-width neural networks.
method Empirical and theoretical analysis of spectra of weight matrices in high-dimensional settings.
result Spectra of weight matrices are invariant under certain training conditions, with implications for feature learning.
Investigates simplicial volume over finite fields and compares it with other coefficients.
problem Examines simplicial volume over Fp coefficients. method Analyzes simplicial volume and gradient invariants over Fp coefficients, comparing with other coefficient rings. result Compares simplicial volumes and Betti numbers over different coefficient rings.
SGD tends to favor simpler subnetworks, improving generalization.
problem SGD's tendency to favor simpler subnetworks over complex ones.
method Identifying invariant sets and analyzing SGD's behavior around them.
result SGD collapses networks to simpler subnetworks, improving generalization.
We will prove the equivariant version of Smale's transversality theorem: suppose that the compact Lie-group G acts on the compact differentiable manifold M on which an invariant Morse-function f and an invariant vector field X are given so that X is gradient-like with respect to f (i.e. X(f)<0 away from critical orbits…
New methods improve adversarial attacks' transferability to other models.
problem Vulnerability of deep learning models to adversarial examples.
method Nesterov Iterative Fast Gradient Sign Method (NI-FGSM) and Scale-Invariant attack Method (SIM).
result NI-FGSM and SIM generate more transferable adversarial examples.
Gradient flow studies Spin(7)-structures on compact 8-manifolds.
problem Formulating and studying the gradient flow of Spin(7)-structures.
method Negative gradient flow of an energy functional of Spin(7)-structures.
result Short-time existence and uniqueness of solutions to the flow.
SGD converges to an invariant distribution with sub-Gaussian or sub-exponential properties.
problem Optimizing smooth and strongly convex objectives using SGD.
method Analysis through Markov chains, focusing on convergence and concentration properties.
result SGD iterates and their invariant limit distribution inherit sub-Gaussian or sub-exponential concentration properties.
Paper approximates risk measures using SGD with Langevin dynamics.
problem Approximating arbitrary law invariant risk measures.
method Stochastic Gradient Langevin Dynamics (SGD-Langevin) for general risk measures.
result Non-asymptotic convergence rates of the approximation algorithm.
For a Hamiltonian action of a compact group U of isometries on a compact Kähler manifold Z and a compatible subgroup G of UC, we prove that for any closed G--invariant subset Y⊂Z the image of the gradient map μp(Y) is independent of the choice of the invariant Kähler form …
We show that gradient shrinking, expanding or steady Ricci solitons have potentials leading to suitable reference probability measures on the manifold. For shrinking solitons, as well as expanding soltions with nonnegative Ricci curvature, these reference measures satisfy sharp logarithmic Sobolev inequalities with low…
Conformally variational Riemannian invariants (CVIs), such as the scalar curvature, are homogeneous scalar invariants which arise as the gradient of a Riemannian functional. We establish a wide range of stability and rigidity results involving CVIs, generalizing many such results for the scalar curvature.
Unique shrinking gradient Kähler-Ricci solitons found on non-compact toric manifolds.
problem Existence and uniqueness of shrinking gradient Kähler-Ricci solitons on non-compact toric manifolds.
method Analyzing properties of Ricci curvature and Lie algebra constraints.
result At most one complete Tn-invariant shrinking gradient Kähler-Ricci soliton on a non-compact toric manifold. New Kähler solitons found that are not U(n)-invariant.
problem Whether every steady gradient Kähler-Ricci soliton of positive curvature on Cn is U(n)-invariant. method Constructing a family of U(1)imesU(n−1)-invariant, but not U(n)-invariant, steady gradient Kähler-Ricci solitons. result Found a family of complete steady gradient Kähler-Ricci solitons with strictly positive curvature operator on Cn for n≥3. GENIE balances domain-invariant feature learning and gradient alignment for improved DG performance.
problem Domain Generalization (DG) overfitting to domain-specific features
method GENIE (Generalization-ENhancing Iterative Equalizer) optimizer
result Prevents a small subset of parameters from dominating optimization, promoting domain-invariant feature learning
The study explores S1-invariant Laplacian flow on 6-manifolds.
problem Finding S1-invariant solutions to the Laplacian flow. method Derive and analyze S1-invariant evolution equations. result Discovery of first inhomogeneous shrinking solitons.
New methods using natural gradient for structured optimization.
problem Structured optimization problems.
method Structured second-order methods via natural gradient descent.
result Efficiency demonstrated on non-convex and deep learning problems.
We study alignment in linear neural networks and its relation to gradient descent.
problem Understanding alignment in linear neural networks and its impact on training.
method Defined alignment for fully connected networks, analyzed alignment under gradient descent, and compared gradient descent to projected gradient descent for layer-constrained networks.
result Gradient descent can converge linearly to a global minimum when alignment is invariant, and alignment is impossible with large datasets in layer-constrained networks.
We make policy optimization algorithms batch size-invariant by decoupling proximal and behavior policies.
problem Some policy optimization algorithms do not have batch size-invariance, leading to inefficiencies.
method We decouple the proximal policy from the behavior policy to achieve batch size-invariance.
result Our approach makes policy optimization algorithms more efficient and allows them to use stale data more effectively.
New theory validates the use of invariant predictors for OOD generalization.
problem Ensuring predictors generalize well across unseen environments.
method Developed new theoretical conditions and derived an Inter Gradient Alignment algorithm.
result Validated the necessity of invariant predictors for OOD optimality.
Rotation invariant algorithms fail on sparse problems even with noise.
problem Rotation invariant algorithms' suboptimality in sparse linear problems with noise.
method Lower bounds and trajectory analysis of optimization algorithms.
result Rotation invariant algorithms are suboptimal even with noise and many examples.
We consider the flows generated by generic gradients of Morse maps of a closed connected manifold M to a circle. To each such flow we associate an invariant counting the closed orbits of the flow. Each closed orbit is counted with the weight derived from its index and homotopy class. The resulting invariant is called…
The complete invariant for gradient like Morse-Smale dynamical systems (vector fields and diffeomorphisms) on closed 4-manifolds are constructed. It is same as Kirby diagram in a case of polar vector field without fixed points of index 3.
This paper provides a geometrical derivation of the Hybrid Minimum Principle (HMP) for autonomous hybrid systems whose state manifolds constitute Lie groups (G,⋆) which are left invariant under the controlled dynamics of the system, and whose switching manifolds are defined as smooth embedded time invariant subma…
Gradient-free framework for Bayesian experimental design in complex systems.
problem Optimal experimental design in systems where gradient information is unavailable.
method Combines EKI and ALDI for optimization and sampling, with approximations for scalable utility estimation.
result Demonstrates robust, accurate, and efficient experimental design in various complex systems.
Gradient-like flows on certain manifolds restrict saddle Morse indices to 1 or n-1.
problem Restricting Morse indices of saddles in gradient-like flows.
method Analyzing invariant manifolds and their intersections for gradient-like flows.
result Morse indices of saddles are either 1 or n-1, no other indices possible.
We study the implicit regularization imposed by gradient descent for learning multi-layer homogeneous functions including feed-forward fully connected and convolutional deep neural networks with linear, ReLU or Leaky ReLU activation. We rigorously prove that gradient flow (i.e. gradient descent with infinitesimal step …
The paper shows averaging gradients leads to memorization, proposing an alternative algorithm to focus on invariances.
problem The principle that 'good explanations are hard to vary' in deep learning is investigated.
method Formalizing consistency for loss surface minima, proposing an alternative algorithm based on logical AND.
result The alternative algorithm prevents memorization and focuses on invariances.
A new method learns graph distributions invariant to node ordering.
problem Graphs are hard to model due to node ordering invariance issues.
method Score-based generative modeling with permutation equivariant graph neural network.
result The method achieves better or comparable graph generation results.
A new biased gradient descent method for conditional stochastic optimization.
problem Challenges in constructing unbiased gradient estimators for conditional stochastic optimization.
method Proposes a biased stochastic gradient descent (BSGD) algorithm and analyzes its sample complexities.
result Establishes sample complexities of BSGD for various objectives and shows that BSpiderBoost matches the lower bound complexity.
DeepHoyer introduces differentiable, scale-invariant sparsity measures for neural networks.
problem Efficiently sparsifying neural networks with scale-invariant sparsity measures.
method Developed DeepHoyer, a set of differentiable, scale-invariant sparsity-inducing regularizers based on the Hoyer measure.
result DeepHoyer produces sparser neural networks than previous methods, maintaining similar accuracy.
Rotation invariant algorithms fail with hard labels sampled from sparse targets.
problem Rotation invariant algorithms fail to learn from hard labels sampled from sparse targets.
method Proving the excess risk of rotation invariant algorithms and proposing a simple non-rotation invariant algorithm.
result Rotation invariant algorithms incur an excess risk of $Ω\left(\frac{d-1}{n}
ight)$, while non-rotation invariant algorithms have an excess risk of $O\left(\frac{s\log d}{n}
ight).
We introduce a scalar invariant on manifolds with density which is analogous to the renormalized volume coefficient v3 in conformal geometry. We show that this invariant is variational and that shrinking gradient Ricci solitons are stable with respect to the associated W-functional.