Full-capacity uRNNs improve performance over restricted-capacity ones.
problem Vanishing and exploding gradient issues in recurrent neural networks.
method Optimized full-capacity unitary recurrence matrices over all unitary matrices.
result Significantly improved performance compared to LSTMs and restricted-capacity uRNNs.
Convexity proven for sums of angles of unitary paths.
problem Proving convexity of sums of eigenvalues of unitary matrices.
method Analyzing paths of unitary matrices and their angles, using operator norms.
result Sum of first m angles of unitary path is convex.
Compactifies Minkowski space using unitary matrices.
problem Compactifying Minkowski space for quantum field theories.
method Using Cayley transform and unitary group $\U(2)$.
result Defines interesting backgrounds for quantum field theories.
Classifies matrices in the quaternionic hyperbolic unitary group.
problem Understanding the structure of matrices in the quaternionic hyperbolic unitary group.
method Used complex representation and characteristic polynomial to study matrices.
result Computed the characteristic polynomial and studied its sign.
Curious structure of special orthogonal, unitary, and symplectic groups as products of Grassmannians discovered.
problem Understanding the structure of special orthogonal, unitary, and symplectic groups.
method Expressing these groups as products of Grassmannians realized as involution matrices.
result Special orthogonal, special unitary, and symplectic groups can be expressed as products of their corresponding Grassmannians.
A major challenge in the training of recurrent neural networks is the so-called vanishing or exploding gradient problem. The use of a norm-preserving transition operator can address this issue, but parametrization is challenging. In this work we focus on unitary operators and describe a parametrization using the Lie al…
We formulate the unitary rational orbifold conformal field theories in the algebraic quantum field theory framework. Under general conditions, we show that the orbifold of a given unitary rational conformal field theories generates a unitary modular category. Many new unitary modular categories are obtained. We also sh…
Private algorithms approximate matrices with private data.
problem Approximate matrices with same spectrum using private data.
method Differential privacy algorithms for unitary orbit optimization.
result Upper and lower bounds on approximation error.
Study of Pascal algebra matrices and their jet bundle map for vector bundles.
problem Defining and studying Pascal algebra matrices and their map on jet bundles.
method Identifying Pascal algebra matrices, showing generator well defines Pascal map, using it for intrinsic contact definition.
result Intrinsic definition of point-wise contact between Hermitian vector bundles using unitary equivalence of Pascal maps.
scoRNN improves RNN performance with simpler orthogonal weight matrices.
problem Vanishing and exploding gradients in RNNs.
method Parametrizing orthogonal recurrent weight matrices with a scaled Cayley transform.
result scoRNN achieves superior results with fewer parameters than other unitary RNNs.
This paper introduces a submanifold of the moduli space of unitary representations of the fundamental group of a punctured sphere with fixed local monodromy. The submanifold is defined via products of involutions through Lagrangian subspaces. We show that the moduli space of Lagrangian representations is a Lagrangian s…
Paper improves tensor completion using unitary transforms.
problem Robust tensor completion for various datasets.
method Transformed tensor SVD with unitary matrices.
result Recovered images have better PSNR than traditional methods.
A Hermitian TQFT from non-semisimple quantum sl(2) modules.
problem Constructing a Hermitian TQFT from a non-semisimple category.
method Endowed a non-semisimple category of quantum sl(2) modules with a Hermitian structure and proved the resulting TQFT is Hermitian.
result Projective representations of the mapping class group in indefinite unitary matrices.
Recurrent neural networks (RNNs) are notoriously difficult to train. When the eigenvalues of the hidden to hidden weight matrix deviate from absolute value 1, optimization becomes difficult due to the well studied issue of vanishing and exploding gradients, especially when trying to learn long-term dependencies. To cir…
We show that for any positive integer n, the maps x∈Cn↦{∣⟨x,zi⟩∣2}i=14n∈R4n, where zi are the columns of four n×n unitary matrices, are generically injective modulo multiplication by a global phase factor, yielding a family of emb…
Random representations of surface groups approach asymptotic freeness in large n limit.
problem Asymptotic freeness of Haar unitary matrices for surface groups.
method Interplay between Dehn's work and classical invariant theory.
result Expected value of trace of a fixed non-identity element is bounded as no∞. A non-singular sesquilinear form is constructed that is preserved by the Lawrence-Krammer representation. It is shown that if the polynomial variables q and t of the Lawrence-Krammer representation are chosen to be appropriate algebraically independant unit complex numbers, then the form is negative-definite Hermitian.…
New theory connects random matrices to surface graphs and mapping class groups.
problem Understanding moments of measures induced by free words on unitary matrices.
method Study measures induced by free words on U(n) and relate to surfaces and mapping class groups.
result Every moment of the measure on U(n) is determined by pairs (Σ, f) involving surfaces and maps.
RUM improves RNN's long-term memory by using unitary matrices.
problem Limited capacity of RNN to manipulate long-term memory.
method Proposes Rotational Unit of Memory (RUM) with unitary matrices.
result RUM learns long-term dependencies and improves state-of-the-art results.
Resolution of a compact group action in the sense described by Albin and Melrose is applied to the conjugation action by the unitary group on self-adjoint matrices. It is shown that the eigenvalues are smooth on the resolved space and that the trivial bundle smoothly decomposes into the direct sum of global one-dimensi…
The Clifford group for 2 qubits is divided into 20 orbits, each with 4608 matrices.
problem Understanding the structure of the Clifford group for 2 qubits.
method Equivalence relation based on local Clifford gates and analysis of orbits.
result The Clifford group for 2 qubits is divided into 20 orbits, each with 4608 matrices.
Solved a specific case of Salter's question on Burau representation.
problem Under what conditions are matrices in the image of the Burau representation of B3. method Algorithmically constructed a counterexample to Salter's specific question.
result The central quotient of the Burau image group is not the central quotient of a certain subgroup of the unitary group.
New invariants derived from random matrices for words in free groups.
problem Defining and understanding new topological invariants for words in free groups.
method Defining and analyzing invariants from w-random matrices and permutations. result Presented new topological, combinatorial, and algebraic invariants of words.
Paper solves a key problem in learning from high-dimensional covariance matrices.
problem Computing normalizing factors for Riemannian Gaussian distributions on high-dimensional covariance matrices.
method Equivalence with random matrix theory and log-normal matrix ensembles to approximate normalizing factors.
result Efficient approximation of normalizing factors with decreasing error as dimension increases.
EUNNs improve RNN performance and efficiency.
problem Gradient explosion/vanishing and long-term correlations in RNNs.
method Unitary matrices with tunable representation capacity and O(1) computational complexity. result EUNNs significantly outperform other RNNs and LSTMs in performance and training speed.
Given a positive and unitarily invariant Lagrangian L defined in the algebra of Hermitian matrices, and a fixed interval [a,b]⊂R, we study the action defined in the Lie group of n×n unitary matrices U(n) by S(α)=∫abL(α˙(t))dt, where α:[a,b]→U(n) is a …
We show that the twisted signature invariants of boundary link concordance derived from unitary representations of the free group are actually ordinary link concordance invariants. We also show how the discontinuity locus of this signature function is determined by Seifert matrices of the link.
Study of strictly accretive matrices using Finsler geometry.
problem Characterize the set of strictly accretive matrices.
method Introduced Finsler metrics and characterized geodesics and distance.
result Geodesic distance applied to matrix approximation problem.
We show that the Nielsen-Thurston classification of mapping classes of the sphere with four marked points is determined by the quantum SU(n)-representations, for any fixed integer n≥2. In the Pseudo-Anosov case we also show that the stretching factor is a limit of eigenvalues of (non-unitary) SU(2)-TQFT represen…
Complex tensor factorization improves knowledge graph completion.
problem Automatically understanding and predicting missing relationships in large knowledge graphs.
method Use of complex-valued embeddings and unitary diagonalization.
result Complex embeddings lead to scalable and expressive models that outperform existing methods.
The paper provides theoretical guarantees for optimized sampling in compressed sensing, showing error vanishes with more measurements.
problem Theoretical and practical improvements in compressed sensing with optimized sampling schemes.
method Theoretical analysis and empirical experiments with optimized sampling schemes for subsampled unitary matrices.
result The error caused by measurement noise vanishes with an increasing number of measurements for optimized sampling schemes, assuming Gaussian noise.
Quantizes Toda systems using geometric methods.
problem Quantizing Toda systems with geometric quantization.
method Geometric quantization of Toda systems as a coadjoint orbit of a group of matrices.
result Found unitary and non-unitary finite dimensional quantum Hilbert spaces.
Clarifies the structure of quantum states using algebraic methods.
problem Unclear stratification of quantum states in physics literature.
method Analyzes the state space S(A) of a finite-dimensional C*-algebra A, focusing on unitary orbits and their properties.
result Identifies a natural Whitney stratification of the state space into matrices of fixed rank, providing a pseudo-manifold structure.
Constructs CAT(0) actions for certain groups without unipotent elements.
problem Understanding actions of certain groups on CAT(0) spaces.
method Constructs an isometric action of a group on a CAT(0) space.
result Fundamental groups of certain 3-manifolds do not admit faithful finite-dimensional unitary representations.
In this paper we discuss the mechanism of spontaneous symmetry breaking from the point view of vacuum pairs, considered as ground states of a Yang-Mills-Higgs gauge theory. We treat a vacuum as a section in an appropriate bundle that is naturally associated with a minimum of a (general) Higgs potential. Such a vacuum s…
Proposes a new RNN structure to improve expressivity without sacrificing stability.
problem Exploding and vanishing gradient problems in RNNs and reduced expressivity.
method Introduces a non-normal RNN structure using Schur decomposition and splitting.
result Enhances expressivity while maintaining stability and training speed.
Quantum neural networks converge to Gaussian processes as they grow.
problem Understanding the convergence of quantum neural networks to Gaussian processes.
method Analyzing Haar random unitary and orthogonal deep QNNs, considering input states, measurement observables, and non-independence of unitary matrix entries.
result Quantum neural networks outputs converge to Gaussian processes in the limit of large Hilbert space dimension.
Researchers study injectivity of magnetic and thermostatic nonabelian ray transforms on compact surfaces.
problem Injectivity of magnetic and thermostatic nonabelian ray transforms on compact surfaces.
method Loop group factorization method for nontrapping λ-geodesic flows and the general linear group of invertible complex matrices. result General injectivity question of the nonabelian ray transform for simple magnetic flows is settled.
Let G be a finite group of complex n by n unitary matrices generated by reflections acting on C^n. Let R be the ring of invariant polynomials, and χbe a multiplicative character of G. Let Ω^χbe the R-module of χ-invariant differential forms. We define a multiplication in Ω^χand show that under this multiplication Ω^χha…
There is an equivalence relation on the set of smooth maps of a manifold into the stable unitary group, defined using a Chern-Simons type form, whose equivalence classes form an abelian group under ordinary block sum of matrices. This construction is functorial, and defines a differential extension of odd K-theory, fit…
ENRNN uses eigenvalue normalization for short-term memory in RNNs.
problem Vanishing/exploding gradient problem and long-term dependency modeling.
method Eigenvalue normalization of recurrent matrix to simulate short-term memory.
result ENRNN outperforms existing RNN variants in experiments.
Random matrix ensembles yield uniform distributions on manifolds.
problem Understanding distributions of vectors in random matrix ensembles.
method Analyzing eigenvalues, singular values, and Autonne-Takagi vectors of various random matrix ensembles.
result Uniform distributions on specific manifolds for different types of random matrix ensembles.
The Riemann sphere of a C*-algebra is a geometric structure derived from a specific projector.
problem Understanding the geometric properties of C*-algebras through their unitary orbits.
method Developed a Riemannian manifold structure on the unitary orbit of a specific projector in a C*-algebra.
result The Riemann sphere is a homogeneous reductive C-infinity manifold with a differential geometry.
Paper solves injectivity of X-ray transform on surfaces.
problem Injectivity of non-Abelian X-ray transform on surfaces.
method Factorization theorem for Loop Groups, energy methods, scalar holomorphic integrating factors.
result Extends results to arbitrary Lie groups.
FastGRNN improves RNN accuracy while drastically reducing model size.
problem Inaccurate training and inefficient prediction in RNNs.
method FastGRNN uses a residual connection and gate to achieve state-of-the-art accuracy with a much smaller model.
result FastGRNN achieves state-of-the-art accuracy with models up to 35x smaller than existing RNNs.
Method quantifies spectral ergodicity in deep learning networks.
problem Understanding the success of deep learning architectures.
method Combines TM and KL divergence metrics to analyze random matrix ensembles.
result Spectral ergodicity increases with network size, suggesting its importance.
Efficiently optimizes CNN and RNN parameters on Stiefel manifold.
problem Computational expense in optimizing orthonormal matrices on Stiefel manifold.
method Cayley transform for efficient retraction and vector transport on Stiefel manifold.
result Cayley SGD and ADAM achieve faster convergence and less training time.
Contact group retracts to unitary subgroup.
problem Understanding contact structures on 3-sphere.
method Proving deformation retraction to unitary subgroup.
result Group of contactomorphisms retracts to U(2).