Flexible ranking models from choice data.
problem Difficulties in modeling, learning from, and predicting rankings.
method Choice-based ranking models using repeated selection.
result Choice-based ranking models outperform existing models in various ranking tasks.
Study improves choice model accuracy and heterogeneity representation using mixture models.
problem Improving prediction accuracy and heterogeneity representation in choice models.
method Semi-nonparametric Latent Class Choice Model with mixture models and EM algorithm.
result Mixture models enhance prediction accuracy and heterogeneity representation without sacrificing interpretability.
New models improve choice prediction accuracy.
problem Model misspecifications in discrete choice models lead to limited predictability and biased estimates.
method Proposes a new approach to estimate choice models by dividing the systematic part into knowledge-driven and data-driven components, which learns a new representation from available variables.
result The new models (L-MNL and L-NL) outperform traditional models in predictive performance and parameter estimation.
Active learning recovers choice model from noisy data.
problem Identifying non-parametric choice models from noisy data.
method Directed acyclic graph (DAG) representation and inclusion-exclusion approach.
result Algorithm more accurately recovers frequent preferences.
New invariants defined for knots and links using quandle representations.
problem Defining new invariants for knots and links.
method Defined a family of quiver representations associated to finite quandles, abelian groups, and quandle 2-cocycles.
result Computed four new polynomial invariants for knots and links.
Paper characterizes MDM for consumer choice modeling and prediction.
problem Modeling consumer choice behavior with parsimonious models.
method Establishes necessary and sufficient conditions for MDM consistency.
result Characterization leads to exact set of representable choice probabilities.
Representation mixing combines character and phoneme inputs for flexible TTS synthesis.
problem Limited control over pronunciation in character or phoneme-based TTS systems.
method Representation mixing combines multiple linguistic inputs in a single encoder.
result Flexibility in choosing between character, phoneme, or mixed representations during inference.
Good predictors of ICU Mortality have the potential to identify high-risk patients earlier, improve ICU resource allocation, or create more accurate population-level risk models. Machine learning practitioners typically make choices about how to represent features in a particular model, but these choices are seldom eva…
Study nonconcave portfolio choice with smooth ambiguity and Bayesian learning.
problem Nonconcave portfolio choice under smooth ambiguity and Bayesian learning.
method Developed a general framework for dynamic, non-concave asset allocation.
result Dynamic consistency achieved through a robust representation.
Develops UKP for comparing feature representations in multitask learning.
problem Comparing feature representations learned by different models without access to test data.
method Uniform Kernel Prober (UKP) for comparing representations in kernel ridge regression tasks.
result UKP provides a uniform measure of prediction error on test data without access to test data.
New model combines neural networks and embeddings for better choice modeling interpretability.
problem Limited behavioral insights in embedding representations for categorical variables.
method Combines discrete choice models and neural networks using embeddings for interpretability.
result Proposed models deliver state-of-the-art predictive performance while preserving interpretability.
Paper uses deep reinforcement learning for optimal stock portfolio management.
problem Optimizing stock portfolio choices in complex market environments.
method Direct deep reinforcement learning to learn factor representations and make optimal decisions.
result Deep learning outperforms average market performance in portfolio allocation.
We present a mixed multinomial logit (MNL) model, which leverages the truncated stick-breaking process representation of the Dirichlet process as a flexible nonparametric mixing distribution. The proposed model is a Dirichlet process mixture model and accommodates discrete representations of heterogeneity, like a laten…
New invariants for virtual knots and links defined via quiver representations.
problem Defining new invariants for virtual knots and links.
method Quiver representations associated to virtual biquandles and rings.
result New polynomial invariants for virtual knots and links.
New polynomial invariants for knots and links.
problem Defining new invariants for knot theory.
method Infinite family of quiver representations.
result Infinite family of two-variable polynomial invariants.
We introduce a certain type of representations for the quantum Teichmuller space of a punctured surface, which we call local representations. We show that, up to finitely many choices, these purely algebraic representations are classified by classical geometric data. We also investigate the family of intertwining opera…
New mutual information framework improves contrastive learning for vision tasks.
problem Maximizing mutual information for better unsupervised learning representations.
method Reformulated mutual information as a lower bound, introducing new negative sampling strategies.
result Improved representations outperform previous methods in various vision tasks.
BERT improves machines' ethical and moral decision-making.
problem Teaching machines ethical and moral choices.
method Applying BERT to human texts to extract moral bias scores.
result BERT improves the moral compass of machines.
Study counterfactuals in combinatorial choice using a representative agent model.
problem Analyzing decision-making from aggregated binary polytope data.
method Nonparametric approach based on a representative agent model, solving polynomial and mixed-integer convex programs.
result Developed a method for counterfactual prediction that works even under model misspecification.
Study subgroup actions on mapping class groups using Heisenberg representations.
problem Untwisting representations of mapping class groups on Heisenberg subgroups.
method Restrict and analyze twisted representations of mapping class groups to Heisenberg subgroups.
result Untwisting representations on Torelli group for any Heisenberg representation.
Extends adjoint representation concept to higher Lie groupoids.
problem Defining adjoint representation for higher Lie groupoids.
method Generalizes standard construction to higher Lie groupoids using simplicial vector bundles.
result Adjoint representation up to homotopy is well-defined and unique.
In this paper, we advocate for representation learning as the key to mitigating unfair prediction outcomes downstream. Motivated by a scenario where learned representations are used by third parties with unknown objectives, we propose and explore adversarial representation learning as a natural method of ensuring those…
The paper categorifies matroid characteristic polynomials using cohomology.
problem Categorifying matroid characteristic polynomials.
method Using quasi-representations, the paper constructs cohomology groups for matroids.
result The cohomology theory generalizes chromatic and characteristic cohomologies.
When applying machine learning to problems in NLP, there are many choices to make about how to represent input texts. These choices can have a big effect on performance, but they are often uninteresting to researchers or practitioners who simply need a module that performs well. We propose an approach to optimizing ove…
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
Study local features of decorated representation spaces for spherical surfaces.
problem Local structure of moduli space of spherical surfaces with conical points.
method Analysis of decorated representation spaces of fundamental groups in SU(2).
result Smooth locus of decorated representation spaces is dense and connected.
This paper aims to incorporate passive symmetries in machine learning for better generalization.
problem Machine learning's reliance on arbitrary choices leads to passive symmetries that can limit generalization.
method Translation among physics, mathematics, and machine learning to understand and implement passive symmetries.
result Respecting passive symmetries can improve machine learning's ability to generalize.
The paper tackles context-dependent choice functions, proposing a model and neural network architectures.
problem Learning choice functions under context-dependent preferences.
method Context-dependent (latent) utility functions, two neural network architectures.
result Demonstrates the effectiveness of the proposed models on synthetic and real-world datasets.
We generalise in this article the Mc Shane-Mirzakhani identities in hyperbolic geometry to arbitrary cross ratios. We give an expression of them in the case of Hitchin representations of surface groups in PSL(n, R) in a suitable choice of Fock-Goncharov coordinates.
Theory of relatively Anosov representations using flow methods.
problem Developing a theory for relatively Anosov representations.
method Using the contracting flow on a bundle to define and study relatively Anosov representations.
result Definition and study of uniformly relatively Anosov representations and a stability result.
Real-valued word representations have transformed NLP applications; popular examples are word2vec and GloVe, recognized for their ability to capture linguistic regularities. In this paper, we demonstrate a {\em very simple}, and yet counter-intuitive, postprocessing technique -- eliminate the common mean vector and a f…
There is a consensus that human and non-human subjects experience temporal distortions in many stages of their perceptual and decision-making systems. Similarly, intertemporal choice research has shown that decision-makers undervalue future outcomes relative to immediate ones. Here we combine techniques from informatio…
We investigate the representation theory of the polynomial core of the quantum Teichmuller space of a punctured surface S. This is a purely algebraic object, closely related to the combinatorics of the simplicial complex of ideal cell decompositions of S. Our main result is that irreducible finite-dimensional represent…
Improved VAE representations lead to better image classification.
problem VAE representations are inferior to non-latent models for image classification.
method Used a decoder that prefers local features, improving global feature capture in latent variables.
result Significant improvement in downstream semantic classification tasks.
A widely applied diversification paradigm is the naive diversification choice heuristic. It stipulates that an economic agent allocates equal decision weights to given choice alternatives independent of their individual characteristics. This article provides mathematically and economically sound choice theoretic founda…
When working with three-dimensional data, choice of representation is key. We explore voxel-based models, and present evidence for the viability of voxellated representations in applications including shape modeling and object classification. Our key contributions are methods for training voxel-based variational autoen…
We provide an axiomatic foundation for the representation of numéraire-invariant preferences of economic agents acting in a financial market. In a static environment, the simple axioms turn out to be equivalent to the following choice rule: the agent prefers one outcome over another if and only if the expected (under t…
SSL theory improves representation learning from raw data.
problem Challenges in SSL, including instability and collapse.
method Precise analysis of generalization performance with a theory-friendly setup.
result Insights for SSL practitioners on data augmentation, network architecture, and training algorithm.
RAE improves image representation learning with simplified design choices.
problem Improving image representation learning using pretrained vision encoders.
method Generalized RAE formulation, complementary working mechanisms of RAE and REPA, and free CFG guidance.
result RAEv2 achieves state-of-the-art results with 10x faster convergence and less training time.
Researchers propose a new SSL risk decomposition method to evaluate and improve self-supervised learning models.
problem Self-supervised learning evaluation is limited to a single metric, providing little insight into model performance and improvement.
method Proposes an SSL risk decomposition that considers four error components: approximation, representation usability, probe generalization, and encoder generalization.
result Analysis of 169 SSL vision models reveals the main sources of error and provides insights for improving SSL models in specific settings.
Unified approach to aggregating models and preferences.
problem Consistent aggregation of models and preferences.
method Formal definition and weighted averaging of models and preferences.
result All rational aggregation rules are weighted averages of highest-ranked models/experts.
Improved sample efficiency in reinforcement learning with object exchangeability.
problem Sample inefficiency in reinforcement learning, especially with complex input structures.
method Attention-based method to project inputs into an efficient representation space invariant under input ordering.
result Our representation reduces the search space by a factor of m! for m objects, improving sample efficiency.
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.
The Ptolemy variety for SL(2,C) is an invariant of a topological ideal triangulation of a compact 3-manifold M. It is closely related to Thurston's gluing equation variety. The Ptolemy variety maps naturally to the set of conjugacy classes of boundary-unipotent SL(2,C)-representations, but (like the gluing equation var…
Simplified feature selection using a single agent with restructured choice strategy.
problem Efficiency and cost issues in multi-agent reinforced feature selection.
method Single-agent approach with restructured choice strategy, including scanning method, feature prioritization, state representation, and reward scheme.
result Improved efficiency and effectiveness of feature selection.
The paper refines disentanglement in VAEs by defining it as latent overlap and prior structure.
problem Improving the disentanglement of latent variables in Variational Autoencoders (VAEs).
method Develops a new perspective on disentanglement as latent overlap and prior structure, and introduces a training objective to control both factors.
result The β-VAE controls latent overlap and maintains prior structure, leading to better disentanglement. Improved representations from multiple video views.
problem Learning reliable representations across unaligned video modalities.
method Correlation-based representation learning on a 4-way parallel multimodal dataset.
result Best models achieve retrieval rates up to 96.9% on open-domain instructional videos.
This paper explores how different audio signal representations affect topological signatures and their predictive power.
problem The impact of different signal representations on topological signatures and their predictive power.
method The study compares three different signal representations (embedding, spectrogram, and spectrogram zeroes) and evaluates their topological signatures for speaker gender, vowel type, and individual prediction.
result Topological signatures from spectrogram zeroes offer the best improvement for gender prediction, and different representations are complementary.