Research
On-device research index

arXiv research

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.

168,657 papers · 148 categories

Trend · papers per month

108215323430 · Jun 202019922001200920172026
48 results for invariant representations

The study analyzes neural network predictions of knot invariants and finds that braid representations work best.

problem Understanding and predicting knot invariants using neural networks.
method Investigated different knot representations and invariants, proposed a cosine similarity score.
result Braid representations are best for predicting knot invariants, and some invariants are easier to learn than others.

Convex learning for diverse invariances in semi-inner-product space.

problem Efficiently learning invariant representations for a wide range of invariances.
method Developed a convex representation learning algorithm for generalized invariances modeled as semi-norms, introducing Euclidean embeddings for kernel representers in a semi-inner-product space.
result Accurate invariant representations learned efficiently and effectively, validated by experiments.

Twisted Alexander invariants have been defined for any knot and linear representation of its group. The invariants are generalized for any periodic representation of the commutator subgroup of the knot group. Properties of the new twisted invariants are given. Under suitable hypotheses, reciprocality and bounds on the …

2010-06-21abs ↗pdf ↗

The paper tackles generalization in machine learning by finding invariant representations of data.

problem Obtaining robust models that generalize well across different training environments.
method The paper introduces the concept of εε-approximate invariance to study the robustness of models to unseen SEMs.
result The paper provides finite-sample out-of-distribution generalization guarantees for approximate invariance in linear SEMs.

A new method evaluates invariant performance of IRM-based representations.

problem Impact of data changes on machine learning model performance.
method Proposes a novel method to evaluate invariant performance of IRM-based representations.
result Establishes a robust criterion to assess invariant performance of various representation techniques.

We give an efficient simplicial formula for the volume and Chern-Simons invariant of a boundary-parabolic PSL(2,C)-representation of a tame 3-manifold. If the representation is the geometric representation of a hyperbolic 3-manifold, our formula computes the volume and Chern-Simons invariant directly from an ideal tria…

2007-10-10abs ↗pdf ↗

Improves contrastive learning invariance with novel training objectives and feature averaging.

problem Contrastive learning's implicit invariance is insufficient for robust performance.
method Introduces a novel training objective and feature averaging approach to enforce invariance.
result Improved performance and robustness to transformations on downstream tasks.

Paper shows regularization improves robustness in domain generalization.

problem Improving robustness in domain generalization.
method Derives novel theoretical analysis to control representation smoothness and proposes a regularization method.
result Regularization improves robustness in domain generalization.

The paper analyzes the tradeoffs between accuracy and invariance in learning representations.

problem Achieving both accuracy and invariance in machine learning models.
method Information theoretic analysis of classification and regression settings.
result Characterization of the accuracy and invariance achievable by any representation of the data.

The paper explores how equivariant models' biases affect latent representations for better performance.

problem The impact of inductive biases on latent representations in equivariant models.
method Demonstrates the importance of accounting for inductive biases in latent representations of equivariant models.
result Effective invariant projections can be used to retain information in latent representations, improving downstream tasks.

The paper reinterprets knot group invariants using affine transformations.

problem Alexander invariants of knots and their geometric interpretation.
method Representation varieties of knot groups into extrmAGL1(C) extrm{AGL}_1(\mathbb{C}).
result Alexander polynomial as the singular locus of a coherent sheaf.

New findings show invariance alone isn't enough to identify latent causal variables.

problem Lack of theoretical insights for identifying latent causal variables when variables are latent.
method Assessed the connection between invariance and causal representation learning using impossibility results.
result Invariance alone is insufficient to identify latent causal variables.

Define quiver representation-valued invariants for classical and virtual knots

problem Define quiver representation-valued invariants for classical and virtual knots
method Define an infinite family of quiver representation-valued invariants of classical and virtual knots associated to a choice of data vector consisting of a biquandle, abelian group, set of biquandle arrows weights with values in the abelian group, coefficient ring and set of biquandle endomorphisms.
result Extract four new polynomial invariants as decategorifications

Representations of data that are invariant to changes in specified factors are useful for a wide range of problems: removing potential biases in prediction problems, controlling the effects of covariates, and disentangling meaningful factors of variation. Unfortunately, learning representations that exhibit invariance …

2018-05-24abs ↗pdf ↗

STAR improves equivariant and invariant representation learning by routing projection heads.

problem Redundant feature learning in equivariant and invariant representation learning.
method Soft Task-Aware Routing (STAR) for projection heads specialization.
result Lower canonical correlations between invariant and equivariant embeddings.

Representations in the auditory cortex might be based on mechanisms similar to the visual ventral stream; modules for building invariance to transformations and multiple layers for compositionality and selectivity. In this paper we propose the use of such computational modules for extracting invariant and discriminativ…

2014-04-01abs ↗pdf ↗

Obtaining common representations from different modalities is important in that they are interchangeable with each other in a classification problem. For example, we can train a classifier on image features in the common representations and apply it to the testing of the text features in the representations. Existing m…

2016-12-23abs ↗pdf ↗

The paper proves properties of quantum representations and their Toledo invariants.

problem Proving properties of quantum representations and their Toledo invariants.
method Computing Toledo invariants for specific quantum representations and extending the concept to a series of cohomological invariants.
result The proof of properties of quantum representations and their Toledo invariants, including the computation of the RR-matrix at first order.

Improves transferability of representations from source to target domains with weights and invariant representations.

problem Label shift between source and target domains in unsupervised domain adaptation.
method Integrates weights and invariant representations to bound the target risk, highlighting the role of inductive bias.
result Empirical evidence shows that weak inductive bias makes adaptation more robust.

Proposes an alternative invariance penalty to address domain generalization issues.

problem Addressing domain generalization problems by finding invariant representations.
method Revisits the Gramian matrix of the data representation to propose an alternative invariance penalty.
result The proposed approach guarantees recovery of an invariant representation under mild conditions.

For an acyclic representation of the fundamental group of a compact oriented odd-dimensional manifold, which is close enough to a unitary representation, we define a refinement of the Ray-Singer torsion associated to this representation. This new invariant can be viewed as an analytic counterpart of the refined combina…

2005-05-25abs ↗pdf ↗

Proposes a method to learn invariant representations for interpretability and fairness.

problem Learning invariant representations to achieve interpretability in algorithmic fairness.
method Adversarially trained model with null-sampling procedure to produce invariant representations in the data domain.
result Shows effectiveness on image and tabular datasets.

Adversarial techniques learn invariant representations across multiple domains.

problem Domain generalization from diverse studies to unseen domains.
method Adversarial censoring techniques for invariant representation learning.
result Limiting behavior of adversarial loss function as the number of domains grows.

The paper proposes a method to create domain-invariant representations using Wasserstein distance.

problem Domain shifts in training data affect machine learning model performance across different domains.
method The method combines classification/regression losses with a GAN-type discriminator to minimize the Wasserstein distance between domains.
result The approach produces the highest minimum classification accuracy and most invariant representation across domains.

Paper develops upper-bounds for target general loss in multiple source DA and DG settings.

problem Complexity and trade-offs in multiple source domain adaptation and domain generalization.
method Defines two types of domain-invariant representations and studies their pros, cons, and trade-offs.
result Developed upper-bounds for target general loss offer insights into domain-invariant representations.

Method learns representations invariant to task-irrelevant details in reinforcement learning tasks.

problem Learning representations that are invariant to task-irrelevant details in reinforcement learning.
method Uses bisimulation metrics to learn robust latent representations that encode only task-relevant information.
result Demonstrates SOTA performance in modified visual MuJoCo tasks and a first-person driving task.