INNs can approximate diverse functions despite layer restrictions.
problem Can INNs approximate sufficiently diverse functions?
method Developed a theoretical framework based on differential geometry to simplify the approximation problem of diffeomorphisms.
result INNs have the universal approximation property.
This work tackles exploding inverses in INNs, revealing and mitigating their numerical non-invertibility.
problem Exploding inverses in INNs cause numerical non-invertibility, leading to failures in various tasks.
method Derived bi-Lipschitz properties of INN building blocks, proposed regularizers for local invertibility, and stable INN designs for global invertibility.
result Bi-Lipschitz properties and stable INN designs are crucial for addressing numerical non-invertibility.
CF-INNs can approximate any invertible function, resolving a long-standing problem.
problem Whether CF-INNs can approximate any invertible function.
method Demonstrated CF-INNs are universal approximators for invertible functions by showing a convenient criterion.
result CF-INNs are universal approximators for invertible functions.
INNs improve acceptance rates in electron spectra analysis.
problem Analyzing electron spectra from near-critical laser-plasmas.
method Invertible Neural Networks (INNs) for forward and inverse modeling.
result INNs significantly increase acceptance rates up to a factor of 10.
INNs produce interval-valued uncertainty scores for DNNs.
problem Uncertainty quantification in deep neural networks.
method Data-driven interval propagating network using interval arithmetic.
result INNs produce sensible lower and upper bounds for prediction error.
In many tasks, in particular in natural science, the goal is to determine hidden system parameters from a set of measurements. Often, the forward process from parameter- to measurement-space is a well-defined function, whereas the inverse problem is ambiguous: one measurement may map to multiple different sets of param…
INN method refines clean labeled data from noisy labels.
problem Handling noisy labels in deep neural networks.
method INN method based on memorization effect at neighbor regions.
result INN method resolves memorization effect shortcomings.
New method uses IB to train normalizing flows for better generative classification.
problem Training generative models with information theory for improved classification.
method Developed IB-INNs, a class of conditional normalizing flows trained with IB objective.
result IB-INNs offer improved uncertainty quantification and out-of-distribution detection compared to traditional generative classifiers.
An automorphism α of a group G is normal if it fixes every normal subgroup of G setwise. We give an algebraic description of normal automorphisms of relatively hyperbolic groups. In particular, we prove that for any relatively hyperbolic group G, Inn(G) has finite index in the subgroup Autn(G) of normal au…
Let A1,...,Ak be a system of free factors of Fn. The group of relative automorphisms Aut(Fn;A1,...,Ak) is the group given by the automorphisms of Fn that restricted to each Ai are conjugations by elements in Fn. The group of relative outer automorphisms is defined as $Out(F_n;A_1,...,A_k) = Aut(F_n…
Let A=A1,...,Ak be a system of free factors of Fn. The group of relative automorphisms Aut(Fn;A) is the group given by the automorphisms of Fn that restricted to each Ai are conjugations by elements in Fn. The group of relative outer automorphisms is defined as $\m…
Multispectral optical imaging is becoming a key tool in the operating room. Recent research has shown that machine learning algorithms can be used to convert pixel-wise reflectance measurements to tissue parameters, such as oxygenation. However, the accuracy of these algorithms can only be guaranteed if the spectra acq…
ISR creates analytical relationships from data via invertible maps.
problem Creating analytical relationships from datasets.
method Combines INNs and EQL, using invertible maps and sparsity promoting regularization.
result ISR can serve as a normalizing flow for density estimation and solve inverse problems.
Stochastic gradient descent (SGD) has been the dominant optimization method for training deep neural networks due to its many desirable properties. One of the more remarkable and least understood quality of SGD is that it generalizes relatively well on unseen data even when the neural network has millions of parameters…
Study bi-Lipschitz equivalence of mixed polynomials under specific conditions.
problem Classify bi-Lipschitz equivalence of mixed polynomials with inner non-degeneracy.
method Defined metric links and introduced new data to determine bi-Lipschitz equivalence.
result Neither Newton boundary nor C-face diagram is an invariant for bi-Lipschitz equivalence.
Intraductal papillary mucinous neoplasm (IPMN) is a precursor to pancreatic ductal adenocarcinoma. While over half of patients are diagnosed with pancreatic cancer at a distant stage, patients who are diagnosed early enjoy a much higher 5-year survival rate of 34% compared to 3% in the former; hence, early diagno…
Study of profinite quandles with constructions and characterizations.
problem Characterizing and constructing profinite quandles.
method Several constructions and characterizations of profinite quandles from profinite groups and other quandles.
result Characterization of algebraically connected profinite quandles in terms of $\widehat{\Inn(Q)}$.
In this paper we study different questions concerning automorphisms of quandles. For a conjugation quandle Q=Conj(G) of a group G we determine several subgroups of Aut(Q) and find necessary and sufficient conditions when these subgroups coincide with the whole group Aut(Q). In particular, we p…
Study confirms non-injective monodromy for even genus 4 translation surfaces.
problem Characterizing monodromy of translation surfaces in even genus 4.
method Analysis of orbifold classifying spaces and finite-type Artin groups.
result Monodromy of Heven(6) contains a non-abelian free group of rank 2. AutoPQ automates quantile forecasting for smart grids, reducing workload and environmental impact.
problem Accurate and unbiased uncertainty quantification in probabilistic forecasting for smart grid operations.
method AutoPQ uses a conditional Invertible Neural Network (cINN) to generate quantile forecasts from point forecasts, automating model selection and hyperparameter optimization.
result AutoPQ outperforms state-of-the-art methods while reducing computational effort and environmental impact.
Factorization Machine (FM) is a widely used supervised learning approach by effectively modeling of feature interactions. Despite the successful application of FM and its many deep learning variants, treating every feature interaction fairly may degrade the performance. For example, the interactions of a useless featur…
Logical neural networks solve mazes by filling dead ends, but not all methods generalize well.
problem Understanding how logical neural networks extrapolate solutions to mazes.
method Examined recurrent and implicit neural networks trained on maze-solving tasks.
result Models fail to generalize well to diverse maze sizes, suggesting limitations in learning scalable algorithms.
New MIP methods improve training of integer-valued neural networks.
problem Training integer-valued neural networks with limited data and resources.
method Formulated new MIP models to optimize training efficiency and handle more data.
result Significantly outperforms previous state-of-the-art methods in accuracy, training time, and data usage.