A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
The paper matches features in images using centro-affine invariants and heat flow.
Bayesian Invariant Prediction models stable features from multi-environment data.
New framework learns sufficient invariant features robustly across distribution shifts.
We add prior knowledge to deep networks to make them invariant to transformations.
We analyze in this paper a random feature map based on a theory of invariance I-theory introduced recently. More specifically, a group invariant signal signature is obtained through cumulative distributions of group transformed random projections. Our analysis bridges invariant feature learning with kernel methods, as …
In this study, a novel feature coding method that exploits invariance for transformations represented by a finite group of orthogonal matrices is proposed. We prove that the group-invariant feature vector contains sufficient discriminative information when learning a linear classifier using convex loss minimization. Ba…
Paper presents a world model that learns invariant causal features using contrastive unsupervised learning.
This paper presents a novel approach to exploit the distinctive invariant features in convolutional neural network. The proposed CNN model uses Scale Invariant Feature Transform (SIFT) descriptor instead of the max-pooling layer. Max-pooling layer discards the pose, i.e., translational and rotational relationship betwe…
A framework isolates and learns approximately shared features for better domain adaptation.
FeAT improves OOD generalization by learning richer features.
CIRCE measures conditional independence for learning invariant features.
New method MRI improves machine learning models' ability to generalize to unseen data.
Interventional domain adaptation improves feature transferability by removing spurious correlations.
New algorithms identify invariant features for domain generalization.
Learning invariant representations is an important problem in machine learning and pattern recognition. In this paper, we present a novel framework of transformation-invariant feature learning by incorporating linear transformations into the feature learning algorithms. For example, we present the transformation-invari…
SFB uses stable features to adapt unstable ones for better performance.
Dida learns meta-features invariant to feature permutations.
ICIL learns policies invariant to multiple environments, improving generalization.
Unsupervised domain adaptation methods aim to alleviate performance degradation caused by domain-shift by learning domain-invariant representations. Existing deep domain adaptation methods focus on holistic feature alignment by matching source and target holistic feature distributions, without considering local feature…
New method improves domain generalization by aligning causal mechanisms across domains.
This work analyzes benefits and limitations of data augmentation and feature averaging in deep learning models.
This paper defines and quantifies transferability in domain generalization.
Proposes IIB for domain generalization, overcoming failure modes of IRM.
Numerous invariant (or equivariant) neural networks have succeeded in handling invariant data such as point clouds and graphs. However, a generalization theory for the neural networks has not been well developed, because several essential factors for the theory, such as network size and margin distribution, are not dee…
Improves contrastive learning invariance with novel training objectives and feature averaging.
We propose a principled method for kernel learning, which relies on a Fourier-analytic characterization of translation-invariant or rotation-invariant kernels. Our method produces a sequence of feature maps, iteratively refining the SVM margin. We provide rigorous guarantees for optimality and generalization, interpret…
Novel framework improves graph learning for out-of-distribution generalization.
A new method extracts features from time series data using iterated sums and improves classification accuracy.
New method selects causal features from diverse data types.
Unordered feature sets are a nonstandard data structure that traditional neural networks are incapable of addressing in a principled manner. Providing a concatenation of features in an arbitrary order may lead to the learning of spurious patterns or biases that do not actually exist. Another complication is introduced …
While several feature scoring methods are proposed to explain the output of complex machine learning models, most of them lack formal mathematical definitions. In this study, we propose a novel definition of the feature score using the maximally invariant data perturbation, which is inspired from the idea of adversaria…
This paper investigates domain generalization: How to take knowledge acquired from an arbitrary number of related domains and apply it to previously unseen domains? We propose Domain-Invariant Component Analysis (DICA), a kernel-based optimization algorithm that learns an invariant transformation by minimizing the diss…
Proposes FSM-IRL to learn invariant network representations considering feature and structural shifts.
Invariance to nuisance transformations is one of the desirable properties of effective representations. We consider transformations that form a \emph{group} and propose an approach based on kernel methods to derive local group invariant representations. Locality is achieved by defining a suitable probability distributi…
TAROT enhances robustness and domain adaptability with domain-invariant features.
New models exploit invariance to reduce model complexity.
In this paper we provide a new Bennequin-type inequality for the Rasmussen- Beliakova-Wehrli invariant, featuring the numerical transverse braid invariants (the c-invariants) introduced by the author. From the Bennequin type-inequality, and a combinatorial bound on the value of the c-invariants, we deduce a new computa…
Breaking symmetry in training data is key for generalization in feature learning kernels.
This work tackles OOD generalization by leveraging causal invariance without needing to recover causal features.
The performance of automatic speech recognition (ASR) systems can be significantly compromised by previously unseen conditions, which is typically due to a mismatch between training and testing distributions. In this paper, we address robustness by studying domain invariant features, such that domain information become…
Suitable lateral connections between encoder and decoder are shown to allow higher layers of a denoising autoencoder (dAE) to focus on invariant representations. In regular autoencoders, detailed information needs to be carried through the highest layers but lateral connections from encoder to decoder relieve this pres…
Deep convolutional neural networks have led to breakthrough results in practical feature extraction applications. The mathematical analysis of these networks was pioneered by Mallat, 2012. Specifically, Mallat considered so-called scattering networks based on identical semi-discrete wavelet frames in each network layer…
Learning domain-invariant representation is a dominant approach for domain generalization (DG), where we need to build a classifier that is robust toward domain shifts. However, previous domain-invariance-based methods overlooked the underlying dependency of classes on domains, which is responsible for the trade-off be…
This paper extends the construction of invariants for virtual knots to virtual long knots and introduces two new invariant modules of virtual long knots. Several interesting features are described that distinguish virtual long knots from their classical counterparts with respect to their symmetries and the concatenatio…
Details of quantum knot invariant calculations using a specific SU(3)_q-module are given which distinguish the Conway and Kinoshita-Teresaka pair of mutant knots. Features of Kuperberg's skein-theoretic techniques for SU(3)_q invariants in the context of mutant knots are also discussed.
SFP prunes ID features to improve OOD generalization without domain data.
Proposes a few-shot learning method for feature selection without labeled data.
Proposes a framework for extracting consistent physiological features across users.