This work improves understanding of reinforcement learning state representations.
problem Lack of precise characterization of how and when state representations generalize.
method Developed a bound on the generalization error based on effective dimension.
result Bound quantifies the tension between generalization and approximation.
dpVAEs improve VAEs by decoupling representation and generation.
problem VAEs struggle with both representation learning and sample generation.
method Introduce decoupled priors (dpVAEs) that separate representation and generation spaces.
result dpVAEs enable regularization without compromising sample generation.
Latent representations are the essence of deep generative models and determine their usefulness and power. For latent representations to be useful as generative concept representations, their latent space must support latent space interpolation, attribute vectors and concept vectors, among other things. We investigate …
Generic Hitchin representations generate dense subgroups.
problem Understanding dense subgroups in SL_n(R) representations.
method Using a theorem by Rapinchuk, Benyash-Krivetz, and Chernousov.
result Generic Hitchin representations are strongly dense.
BigBiGAN improves unsupervised representation learning using image generation quality.
problem Improving unsupervised representation learning methods.
method Extending BigGAN to include an encoder and modifying the discriminator for representation learning.
result BigBiGAN models achieve state-of-the-art performance in unsupervised representation learning and unconditional image generation.
Survey on affine Anosov representations and their implications.
problem Generalizing Anosov representations to affine settings.
method Discussion and survey of existing work.
result Implications of affine Anosov representations.
Let G be a Lie group and Q a quiver with relations. In this paper, we define G-valued representations of Q which directly generalize G-valued representations of finitely generated groups. Although as G-spaces, the G-valued quiver representations are more general than G-valued representations of finitely generated group…
GGAN improves audio representation learning with fewer labels.
problem Learning representations for specific tasks from unlabelled data.
method Guided Generative Adversarial Neural Network (GGAN).
result GGAN learns better representations with fewer labelled data.
VTAB benchmarks diverse visual tasks to assess representation learning effectiveness.
problem Lack of a unified evaluation for general visual representations.
method Developed VTAB, a benchmark for diverse visual tasks, and evaluated many representation learning algorithms.
result VTAB revealed insights into the effectiveness of various representation learning methods.
Theory of Θ-positive representations for real closed fields.
problem Generalizing positive representations to real closed fields.
method Developing theory for Fuchsian groups to linear groups over real closed fields.
result Theory encompasses many generalizations of positive or Anosov representations.
Long and Moody gave a method of constructing representations of the braid group B_n. We discuss some ways to generalize their construction. One of these gives representations of subgroups of B_n, including the Gassner representation of the pure braid group as a special case. Another gives representations of the Hecke a…
Advances in neural network based classifiers have transformed automatic feature learning from a pipe dream of stronger AI to a routine and expected property of practical systems. Since the emergence of AlexNet every winning submission of the ImageNet challenge has employed end-to-end representation learning, and due to…
Generative concept representations have three major advantages over discriminative ones: they can represent uncertainty, they support integration of learning and reasoning, and they are good for unsupervised and semi-supervised learning. We discuss probabilistic and generative deep learning, which generative concept re…
CADE learns dual node representations for better generalization.
problem Transductive graph embeddings cannot generalize to unseen nodes or across different graphs.
method CADE combines real-time neighborhoods with neighbor-attentioned representation, preserving known node memory.
result CADE outperforms state-of-the-art methods in generalization and context-awareness.
Proposes a new framework for image generation using classification latent space representations.
problem Combining discriminative and dense representations for image generation and reconstruction.
method Discriminative modeling framework using manipulated supervised latent representations.
result Higher classification accuracy and visually realistic image generation compared to existing models.
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.
New representations of surface groups into higher-dimensional PSL generalize pleated surfaces.
problem Generalizing pleated surfaces to higher-dimensional PSL groups.
method λ-Borel Anosov representations of surface groups into PSL_d(C).
result Holomorphic parametrization of space of (λ,d)-pleated surfaces.
New representation theory for closed geodesic subflows.
problem Classifying representations with good geometric properties.
method Restricting to invariant closed geodesic subflows.
result Equivalent characterizations and properties of new representations.
Unified framework for learning function representations using INRs and Transformers.
problem Scalability and efficiency limitations in existing generative models.
method Integrates INRs and Transformer-based hypernetworks into latent variable models.
result Improved scalability, expressiveness, and generalization over existing models.
The paper introduces models to learn generalized transformation equivariant representations.
problem Capturing intrinsic visual structures equivariant to various transformations.
method Deterministic and probabilistic AutoEncoding Transformations (AET and AVT) models trained to learn visual representations from generic groups of transformations.
result Generalized TERs (GTERs) that are equivariant to transformations in a more general fashion.
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.
TCRI improves domain generalization by enforcing conditional independence constraints.
problem Limitations of existing domain generalization methods due to incomplete constraints.
method TCRI implements regularizers motivated by conditional independence constraints.
result TCRI achieves cross-domain stability and outperforms baselines in worst-domain accuracy.
Robust reinforcement learning agents generalize well to out-of-distribution settings using pretrained representations.
problem Achieving sample-efficient reinforcement learning agents that generalize to real-world settings.
method Trained 240 representations and 10,000 RL policies on a simulated robotic setup, evaluating different pretrained VAE-based representations' effects on OOD generalization.
result Many reinforcement learning agents are surprisingly robust to realistic distribution shifts, including sim-to-real cases.
Researchers describe unitary representations of mixed braid groups.
problem Understanding unitary representations of mixed braid groups.
method Explicitly describe unitary representations on cohomology of Abelian branched covers.
result Image of the representation is generated by complex reflections and related to the multivariate Burau representation.
Method learns state representations without supervision for Atari games.
problem Learning state representations without supervision.
method Maximizes mutual information across features of neural encoder.
result New benchmark for evaluating representation learning models.
DBGAN learns graph node representations by balancing distribution consistency.
problem Graph representation learning overfits due to ignoring data distribution.
method DBGAN uses a structure-aware prior distribution and bidirectional adversarial learning.
result DBGAN achieves better trade-off between robustness and dimensionality.
The paper introduces cataclysm deformations for Anosov representations.
problem Deforming Anosov representations in Lie groups.
method Constructing cataclysm deformations for θ-Anosov representations into semisimple Lie groups. result Cataclysm deformations are injective for Hitchin representations but not for all θ-Anosov representations. The paper formalizes how concepts are encoded in text-guided generative models and provides a method to manipulate them.
problem Encoding and manipulating concepts in text-guided generative models.
method Formalizing concepts as subspaces of a representation space, developing algebraic manipulation methods.
result The ability to manipulate concepts in generative models through algebraic operations on the representation.
EC^2-VAE generates music analogies by disentangling pitch and rhythm representations.
problem Disentangling music representations for generating creative analogies.
method Explicitly-constrained variational autoencoder (EC^2-VAE) for disentangling pitch and rhythm representations.
result EC^2-VAE enables the generation of music analogies by borrowing representations from different pieces.
Proposes GAAE for high-fidelity audio generation and representation learning.
problem Lack of usable representations and high-fidelity audio generation from unsupervised learning.
method Guided Adversarial Autoencoder (GAAE) leveraging a small percentage of labelled data.
result Generates high-fidelity audio with superior quality and learns powerful representations.
This thesis investigates unsupervised time series representation learning for sequence prediction problems, i.e. generating nice-looking input samples given a previous history, for high dimensional input sequences by decoupling the static input representation from the recurrent sequence representation. We introduce thr…
New representations of Lie algebras via monoidal category actions.
problem Constructing representations of Lie algebras using monoidal categories.
method Using crossed homomorphisms and monoidal categories to generate representations.
result Established new bifunctor for weak and admissible representations of Lie-Rinehart algebras.
Representations of the Iwahori-Hecke algebra of type A_{n-1} are equivalent to representations of the braid group B_n for which the generators satisfy a certain quadratic relation. We show how to construct such representations from the natural action of B_n on the homology of configuration spaces of the punctured disk.…
We characterize groups admitting Anosov representations into SL(3,R), projective Anosov representations into SL(4,R), and Borel Anosov representations into SL(4,R). More generally, we obtain bounds on the cohomological dimension of groups admitting Pk-Anosov r…
Study k-positive surface group representations and their degenerations.
problem Understanding the behavior of surface group representations under degenerations.
method Introduced k-positive representations and studied their degenerations using a limit theorem for positively ratioed representations.
result Degenerations of k-positive representations can lead to limits that are at least (k-3)-positive and irreducible limits are (k-1)-positive.
Researchers develop multi-utility representations for incomplete preferences linked to risk measures.
problem Handling incomplete preferences induced by set-valued risk measures.
method Established dual representations of set-valued risk measures to create parsimonious and well-behaved multi-utility representations.
result Unified dual representations of set-valued risk measures, linking them to scalar risk measures.
Researchers compute determinants and torsions of Rumin complex in specific Lie group representations.
problem Computing determinants and torsions of Rumin complex in specific Lie group representations.
method Analyzing Schrodinger and generic representations of the (2,3,5) nilpotent Lie group.
result Computed the spectrum and zeta regularized determinant of Rumin differentials in Schrodinger representations and evaluated their alternating product in generic representations.
Generic Hitchin representations avoid hyperplanes in Lie algebras.
problem Properties of Hitchin representations in Lie algebras.
method Defined J(ρ) and used hyperplanes in Lie algebras to show J(ρ)∩H=∅. result Generic G-Hitchin representations avoid hyperplanes in the Lie algebra of G. We provide a dual representation of quasiconvex maps between two lattices of random variables in terms of conditional expectations. This generalizes the dual representation of quasiconvex real valued functions and the dual representation of conditional convex maps.
Proves EGF representations in specific geometric contexts.
problem Understanding representations of groups with hyperbolic properties.
method Analyzes projectively convex cocompact manifolds and convex projective manifolds with generalized cusps.
result Holonomy representations of specific geometric manifolds are EGF representations.
New representations defined for groups and graphs, with applications to stable representations.
problem Defining and constructing new types of representations for groups and graphs.
method Introducing (R,Λ)-directed Anosov representations and using Fock-Goncharov positivity to construct them. result Constructs large families of primitive stable representations from F2 to PGL(V), including non-discrete and non-faithful examples. New method learns disentangled discrete representations using categorical variational autoencoders.
problem Learning disentangled representations from discrete latent spaces.
method Replaced standard Gaussian VAE with a categorical VAE to mitigate rotational invariance.
result Categorical distributions improve learning of disentangled representations.
Study Heisenberg homology on surface configurations, revealing new representations of mapping class groups.
problem Homology of surface configurations with Heisenberg group representations.
method Analysis of unordered configurations in a surface, using Heisenberg group actions and representations.
result Obtained genuine and projective representations of mapping class groups from Heisenberg group actions.
iREPA shows spatial structure, not global semantic, drives generation performance in REPA.
problem Understanding what aspect of the target representation matters for generation.
method Empirical analysis of 27 vision encoders, two modifications to REPA.
result Spatial structure, not global semantic, drives generation performance.
We give a formula of the colored Alexander invariant in terms of the homological representation of the braid groups which we call truncated Lawrence's representation. This formula generalizes the famous Burau representation formula of the Alexander polynomial.
New method learns low-dimensional representations of AI-generated treatments.
problem Representing AI-generated treatments without losing semantic meaning.
method Double kernel representation learning with alternating minimization.
result Efficiently learned representations guide generative models and facilitate adaptive online experiments.
Researchers parametrize spaces of positive representations for Lie groups.
problem Tackling spaces of positive representations for Lie groups.
method Generalizing Lusztig's total positivity, they introduce spaces of positive framed representations and parametrize them.
result The number of connected components of the space of framed positive representations agrees with the number of positive representations.
Study parabolic representations of knots using quandles and polynomials.
problem Classify parabolic representations of knot groups.
method Utilize parabolic and symplectic quandles, generalized Riley polynomials, and u-polynomials. result Complete classification of parabolic representations up to 12 crossings.