Paper presents a world model that learns invariant causal features using contrastive unsupervised learning.
problem Learning invariant causal features in unsupervised settings.
method Contrastive unsupervised learning with intervention invariant auxiliary task.
result Significantly outperforms state-of-the-art methods on out-of-distribution point navigation tasks.
Regularizes RNNs to be invariant to input order.
problem Making RNNs invariant to input order.
method Stochastic regularization to enforce permutation invariance.
result Improves model performance on permutation invariant tasks.
The paper analyzes counterfactual invariance and its relation to conditional independence.
problem Understanding the relationship between counterfactual invariance and conditional independence.
method Theoretical analysis of existing definitions, graphical implications, and mathematical proofs.
result Counterfactual invariance implies conditional independence, but not the other way around.
Bayesian Invariant Prediction models stable features from multi-environment data.
problem Analyzing stable features across multiple environments for better prediction and understanding.
method Developed Bayesian Invariant Prediction (BIP) model that encodes invariant feature indices as latent variables and infers them via posterior inference.
result BIP and its variational approximation (VI-BIP) outperform existing methods in accuracy and scalability for invariant prediction.
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 ε-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.
Proposes a supervised VAE to reveal model invariances for interpretability.
problem Understanding and interpreting complex supervised models.
method Supervised variational auto-encoders (VAEs) with latent space invariances.
result Reveals model invariances through sampling nuisance dimensions.
Paper introduces effect-invariance for better policy generalization.
problem Adapting policies to unseen environments efficiently.
method Introduces effect-invariance, a relaxation of full invariance, and develops testing procedures to test e-invariance directly from data.
result Effect-invariance enables zero-shot and few-shot policy generalization without assuming a causal graph.
This paper explains how model invariance improves generalization using data transformations.
problem Understanding why model invariance leads to better generalization performance.
method Introducing sample cover induced by transformations and refining generalization bounds.
result The sample covering number can be used to evaluate and select suitable data transformations.
Proposes learning invariances in neural networks using a weight-space approach.
problem Learning invariances from data in neural networks remains an open problem.
method Minimizes a lower bound on the marginal likelihood in weight space.
result Results in higher performing models with naturally learned invariances.
ADIGen: Automatic, Debiased, and Invariant Counterfactual Generation
problem Generative models for counterfactual outcomes
method ADIGen combines Riesz regression, causal invariance, and orthogonal statistical learning
result ADIGen controls counterfactual risk under general interventions
New models exploit invariance to reduce model complexity.
problem Reducing model complexity for tasks with inherent invariances.
method Invariant random features and kernel methods.
result Exploiting invariance saves a dα factor in model complexity. 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.
GALA framework learns invariant graph representations via environment augmentation with minimal assumptions.
problem Learning invariant graph representations from different environments without additional assumptions.
method Developed GALA framework with minimal assumptions of variation sufficiency and consistency. Uses an assistant model to differentiate graph environment changes.
result Extracting maximally invariant subgraphs to proxy predictions identifies underlying invariant subgraphs for successful out-of-distribution generalization.
Regularising for invariance to data augmentation improves machine learning models.
problem Improving generalization in machine learning models through data augmentation.
method Explicit regularisation to encourage invariance at the level of individual model predictions.
result Explicit regularisation improves generalization and equalizes performance differences between objectives.
New framework learns sufficient invariant features robustly across distribution shifts.
problem Learning robust models under distribution shifts between training and test datasets.
method Sufficient Invariant Learning (SIL) framework and Adaptive Sharpness-aware Group Distributionally Robust Optimization (ASGDRO) algorithm.
result Empirical evaluations confirm ASGDRO's robustness against distribution shifts.
The study identifies two sources of invariants in 2--nondegenerate CR geometries.
problem Characterizing fundamental invariants of 2--nondegenerate CR geometries.
method Analyzes the harmonic curvature and the difference in complex structures.
result Nontrivial examples of CR geometries can be obtained as deformations of models.
This work provides statistical guarantees for GANs that are invariant to certain group symmetries.
problem Learning group-invariant distributions efficiently.
method Study of group-invariant GANs and their performance guarantees.
result Group-invariant GANs require fewer samples and have a reduced discriminator approximation error.
The paper tackles spurious correlations in machine learning models and introduces counterfactual invariance.
problem Spurious correlations in machine learning models that depend on irrelevant parts of input data.
method The paper uses causal inference to stress test models and introduces counterfactual invariance as a formal requirement.
result Counterfactual invariance is a requirement for models to be robust to irrelevant perturbations in input data.
Study invariant connections on multivariate Gaussian distributions.
problem Understanding statistical connections on multivariate Gaussian distributions.
method Investigate invariant connections on N0n with the Fisher metric. result Explicitly determined invariant connections and their moduli spaces.
Bayesian network learns data invariances without augmentation.
problem Learning invariances in neural networks without manual design.
method Bayesian approach infers weight-sharing schemes from data.
result Model outperforms non-invariant networks on specific tasks.
We recall the definition of the quadratic helicity invariant and of the higher asymptotic ergodic M-invariant. We present a simpler new proof (in part) that the M-invariant is ergodic. The M-invariant is a higher invariant, this means that for the magnetic field with closed magnetic lines the invariant is not a f…
Formulae for Vassiliev invariants derived from Kauffman polynomial.
problem Computing Vassiliev invariants from knot polynomials.
method State model of Kauffman polynomial, Gauss diagram identities, arrow diagram identities.
result Gauss diagram formulae for Vassiliev invariants of order 3.
Our work improves VAE latent space clustering by enforcing invariant and equivariant learning.
problem Current VAEs fail to learn invariant and equivariant clusters in latent space.
method We use a mixture model pdf like Gaussian mixtures to enforce deep, group-invariant learning and separate semantic and equivariant variables.
result Our model effectively learns to disentangle invariant and equivariant representations, improving learning rate and image recognition.
GCNNs gain rotation invariance with more training augmentation, making SVD-Universal more effective.
problem Improving robustness of GCNNs to adversarial attacks.
method SVD-Universal technique applied to GCNNs trained with larger rotations.
result SVD-Universal becomes more effective as GCNNs gain rotation invariance.
ATLAS separates invariant and transferable latent factors across diverse environments.
problem Transfer learning and robust prediction in heterogeneous environments.
method ATLAS leverages invariance principle to disentangle latent factors and uses auxiliary labels for robust prediction.
result Near-oracle performance and robust transferable prediction in new environments.
A new quantum gauge model is proposed. From this quantum gauge model we derive a quantum invariant of 3-manifolds. We show that this quantum invariant of 3-manifolds gives a classification of closed (orientable and connected) 3-manifolds. From this classification we then prove the Poincaré conjecture.
We introduce and study in detail an invariant of (1,1) tangles. This invariant, derived from a family of four dimensional representations of the quantum superalgebra U_q[gl(2|1)], will be referred to as the Links-Gould invariant. We find that our invariant is distinct from the Jones, HOMFLY and Kauffman polynomials (de…
Model for assembly map of bordism-invariant functors.
problem Understanding assembly maps of bordism-invariant functors.
method Categorical model using oplax colimits of stable, hermitian, and Poincaré categories.
result Explicit description of the kernel of the assembly map.
Estimates model performance under distribution shift using domain-invariant predictors.
problem Poor performance of models on test distributions different from training distributions.
method Uses domain-invariant predictors as a proxy for unknown target labels.
result Shows that the complexity of latent representations influences target risk.
Proposes a method to learn stable invariant sets in dynamical systems.
problem Learning stable invariant sets in general dynamical systems.
method Generalizes Manek and Kolter's approach by introducing projection onto latent space shapes and using invertible neural networks.
result Validates the method and shows its usefulness for long-term prediction.
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.
Expository observation on the μ-invariant of singularity models for Ricci Flow.
Invariant Causal Set Covering Machines avoid spurious associations.
problem Learning algorithms for rule-based models are vulnerable to spurious associations.
method Building on invariant causal prediction, propose Invariant Causal Set Covering Machines for conjunctions/disjunctions of binary-valued rules.
result The method can identify causal parents of a variable of interest in polynomial time.
The paper studies differential operator invariants and equivalence under Lie pseudogroups.
problem Understanding invariants and equivalence of differential operators under Lie pseudogroups.
method Analysis of invariants, use of n-invariants, and application of local symplectomorphisms as an example.
result Normal forms and solutions to equivalence problems for differential operators.
Study algebraic invariants from lightning self-attention models.
problem Understanding polynomial coefficients of self-attention mechanisms.
method Identify algebraic invariants using polynomial coefficients and coordinate geometry.
result Found linear and nonlinear families of algebraic invariants.
FAIR-NN finds invariant variables for causal inference across diverse environments.
problem Nonparametric invariance and causal learning in regression models with varying joint distributions.
method FAIR-NN framework using adversarial optimization and neural networks.
result FAIR-NN identifies invariant variables and quasi-causal variables under minimal conditions.
Learn invariances in neural networks by optimizing over augmentation parameters.
problem Lack of knowledge about present invariances and their extent in data.
method Parameterize a distribution over augmentations and optimize network parameters and augmentation parameters simultaneously.
result Recover correct set and extent of invariances on various tasks from training data alone.
SenSeI ensures fair models by enforcing invariance on sensitive groups.
problem Ensuring fair machine learning models that respect sensitive groups.
method Designing a transport-based regularizer to enforce invariance on sensitive sets.
result Certifiably fair ML models trained using SenSeI achieve improved fairness metrics.
Abstract summarizes level-rank duality in knot and link invariants.
problem Distinguishing torus knots and links from hyperbolic ones.
method Chern-Simons theory and tables of knot invariants.
result Criterion to distinguish torus knots and links from hyperbolic ones.
We study random knots and links in R^3 using the Petaluma model, which is based on the petal projections developed by Adams et al. (2012). In this model we obtain a formula for the distribution of the linking number of a random two-component link. We also obtain formulas for the expectations and the higher moments of t…
ReCoRe learns invariant features for world navigation using contrastive learning and regularizers.
problem Limited sample efficiency and overfitting to training scenarios in RL for visual navigation.
method Contrastive unsupervised learning and intervention-invariant regularizer.
result Significantly improves sample efficiency and generalization in out-of-distribution point navigation tasks.
The paper explores how to make machine learning models robust to domain shifts.
problem Machine learning models are unreliable in domains different from training.
method Introducing a broad formal notion of invariance and causal structures.
result The true underlying causal structure of the data plays a critical role in robustness.
Learning generative models for graph-structured data is challenging because graphs are discrete, combinatorial, and the underlying data distribution is invariant to the ordering of nodes. However, most of the existing generative models for graphs are not invariant to the chosen ordering, which might lead to an undesira…
New quantum invariants for planar knotoids improve knot classification.
problem Classifying and distinguishing planar knotoids with up to five crossings.
method Define biframed planar knotoids and construct new invariants.
result Improved classification of planar knotoids with up to five crossings.
A key problem in computational material science deals with understanding the effect of material distribution (i.e., microstructure) on material performance. The challenge is to synthesize microstructures, given a finite number of microstructure images, and/or some physical invariances that the microstructure exhibits. …
The ``Links-Gould invariant'' is a two-variable Laurent polynomial invariant of oriented (1,1) tangles, which is derived from the representation of the braid generator associated with the one-parameter family of four dimensional representations with highest weights (0,0|a) of the quantum superalgebra U_q[gl(2|1)]. We u…
A three dimensional supergravity theory which generalizes the super IG theory of Witten and resembles the model discussed recently by Mann and Papadopoulos is displayed. The partition function is computed, and is shown to be a three-manifold invariant generalizing the Casson invariant.
The Grassmannian model represents harmonic maps from Riemann surfaces by families of shift-invariant subspaces of a Hilbert space. We impose a natural symmetry condition on the shift-invariant subspaces that corresponds to considering an important class of harmonic maps into symmetric and k-symmetric spaces. In parti…