Kernel Bayes' rule fails to produce natural predictions in some cases.
problem Kernel Bayes' rule produces unnatural predictions in certain scenarios.
method Kernel Bayes' rule as a nonparametric method in reproducing kernel Hilbert spaces.
result Kernel Bayes' rule fails to produce natural predictions in some cases.
Until recently, Ricci flow was viewed almost exclusively as a way of deforming Riemannian metrics of bounded curvature. Unfortunately, the bounded curvature hypothesis is unnatural for many applications, but is hard to drop because so many new phenomena can occur in the general case. This article surveys some of the th…
Natural gradient descent is a robust optimization method for machine learning.
problem Training poorly parameterized networks efficiently.
method Optimization algorithms with natural transformation properties.
result Optimization algorithms with natural transformation properties are more efficient for poorly parameterized networks.
Study solves utility maximization in a transient price impact market.
problem Utility maximization in a market with transient price impact.
method Developed a discrete-time model and removed market depth and resilience process restrictions.
result Solved the utility maximization problem without convexity of attainable portfolio values.
Shows self orbit equivalences of Anosov flows on 3-manifolds have specific properties.
problem Characterizing self orbit equivalences of Anosov flows on 3-manifolds.
method Analyzing the homotopy properties and orbit structure of self orbit equivalences.
result Self orbit equivalences of Anosov flows on 3-manifolds are restricted to specific types.
This study detects fake and automated accounts on Instagram.
problem Fake engagement on Instagram leads to financial loss and wrong audience targeting.
method Two datasets were created and machine learning algorithms like Naive Bayes, Logistic Regression, Support Vector Machines, Neural Networks, and cost-sensitive genetic algorithm were applied.
result 86% accuracy for automated accounts and 96% for fake accounts were achieved.
We have numerically simulated the ideal-gas models of trading markets, where each agent is identified with a gas molecule and each trading as an elastic or money-conserving two-body collision. Unlike in the ideal gas, we introduce (quenched) saving propensity of the agents, distributed widely between the agents ($0 \le…
HiP-MDPs help personalize HIV treatment across patient variations.
problem Physiological variation leads to different responses to treatments.
method Embed tasks in a low-dimensional space, updating HiP-MDP framework.
result Robust personalized medicine strategies developed for HIV treatment.
Physicists explain a mathematical theorem about topological insulators.
problem Mathematical formulation of APS index theorem not directly related to physical fermion system.
method Reformulated APS index theorem using η invariant of domain-wall Dirac operator.
result Equivalence between APS index and η invariant is generally true.
Empirical Bayes method for Boltzmann machines avoids computational hardness.
problem Estimating hyperparameters of Boltzmann machines with intractable integrations.
method Replica method and Plefka expansion to avoid integrations.
result Simple and fast algorithm with a bias in estimates.
GLAD improves latent graph generation by quantizing discrete latent space.
problem Latent space graph generative models lack performance and make unnatural assumptions.
method Adapting diffusion bridges to a discrete latent space, avoiding data space decompositions.
result GLAD achieves competitive performance on graph benchmark datasets.
New research shows that the dimension gap between intrinsic and ambient dimensions affects adversarial vulnerability of machine learning models.
problem The mystery of adversarial attacks on machine learning models.
method Introducing two types of adversarial attacks and proving their relationship to the dimension gap.
result The dimension gap between intrinsic and ambient dimensions makes clean-trained models more vulnerable to off-manifold adversarial perturbations.
Our work proves convergence to low robust training loss for polynomial width ReLU networks.
problem Understanding why adversarial training leads to low robust training loss in over-parameterized neural nets.
method Extending convergence theory for standard supervised training to adversarial training, using tools from online learning and showing ReLU networks can approximate the step function.
result Convergence to low robust training loss for polynomial width ReLU networks under natural assumptions.
RFM improves CNFs by adding a boundary constraint term and matching velocity fields.
problem Flow matching on constrained domains leads to unnatural samples.
method RFM adds a boundary constraint term and matches velocity fields in a simulation-free manner.
result RFM achieves comparable or better results on standard image benchmarks and produces high-quality samples.
Improves naturalness in TTS samples using quantized VAE and auto-regressive prosody.
problem Discontinuous and unnatural speech from standard VAE priors.
method Discretized latent features using vector quantization (VQ), and separately trained autoregressive (AR) prior model.
result Significantly improves naturalness in random sample generation.
This work improves online fine-tuning of diffusion models for specific properties.
problem Efficiently fine-tuning diffusion models to maximize specific properties.
method A novel reinforcement learning procedure that efficiently explores feasible samples.
result The method provides a regret guarantee and empirical validation across multiple domains.
Reflected Diffusion Models improve on score-based models by incorporating data constraints.
problem Numerical error in score-based models leads to unnatural samples.
method Reverses a reflected stochastic differential equation on data support, learning perturbed score function through generalized score matching loss.
result Improves sample quality and fidelity without architectural modifications.
Improved autoencoder for F0-consistent voice conversion.
problem Non-parallel many-to-many voice conversion with prosodic information leakage.
method Conditional autoencoder with information-constraining bottlenecks.
result Controlled F0 contour and improved speech quality.
``An orbifold is a space which is locally modeled on the quotient of a vector space by a finite group.'' This sentence is so easily said or written that more than one person has missed some of the subtleties hidden by orbifolds. Orbifolds were first introduced by Satake under the name ``V-manifold'' and rediscovered by…
Unified framework for non-Euclidean CPD under scalable stochastic mirror descent.
problem Handling non-Euclidean losses in tensor decomposition.
method Tensor fiber sampling strategy-based stochastic mirror descent.
result Global convergence to a stationary point under reasonable conditions.
Boosting VI improves inference by greedily combining densities.
problem Improving tractability in Bayesian statistics.
method Adapting boosting techniques to VI, replacing a single density with a mixture of densities.
result Demonstrates convergence of boosting VI under relaxed smoothness assumptions.
Bayesian approach uses deep learning for seismic imaging and uncertainty quantification.
problem Uncertainty in seismic imaging due to nonuniqueness and noise.
method Implicit structured prior from randomly initialized convolutional neural network, combined with Bayesian model averaging and stochastic gradient Langevin dynamics.
result Deep priors reduce imaging artifacts and overfitting in noisy conditions.
The optimistic limit is the mathematical formulation of the classical limit which is a physical method to expect the actual limit by using saddle point method of certain potential function. The original optimistic limit of the Kashaev invariant was formulated by Yokota, and a modified formulation was suggested by the a…
GENESIS-V2 infers unordered object representations without iterative refinement.
problem Unsupervised learning of unordered object representations for complex images.
method Stochastic stick-breaking process for clustering pixel embeddings.
result GENESIS-V2 outperforms recent baselines in unsupervised image segmentation and scene generation.
Novel stability bounds for OT maps improve density estimation.
problem Estimating optimal transport maps between probability distributions.
method Developed novel stability bounds for OT maps, reducing the problem to density estimation.
result Stability bounds allow for sharper guarantees without smoothness assumptions.
We develop a calculus of surgery data, called bridged links, which involves besides links also pairs of balls that describe one-handle attachements. As opposed to the usual link calculi of Kirby and others this description uses only elementary, local moves(namely modifications and isolated cancellations), and it is val…
Analyzes D-branes in string theory backgrounds using advanced cohomology.
problem Classifying gauge theories and D-brane world-volumes in string theory.
method Detailed analysis of partially non-abelian Deligne cohomology and twisted differential K-theory.
result Complete characterization of D-brane world-volumes and topological charges.
Transformer struggles with arithmetic length but improves with explicit structure encoding.
problem Transformers fail to generalize length in arithmetic tasks.
method Explicitly encoding structural symmetries via modified number formatting and custom positional encodings.
result Transformer can generalize up to 50-digit numbers without additional data.
Feature normalization prevents collapse in non-contrastive learning dynamics.
problem Non-contrastive learning can collapse into a single point due to lack of repulsive force.
method Extended previous theory based on L2 loss to cosine loss, considering feature normalization.
result Cosine loss induces stable equilibrium, preventing collapse even with insufficient repulsive force.
New methods tackle robust reinforcement learning in sparse, corrupted data.
problem Tackles robust reinforcement learning in sparse, corrupted data.
method Proposes actor-critic methods with sparse robust estimator oracles.
result First non-vacuous guarantees in high-dimensional sparse MDPs with single-policy concentrability coverage.
Proposes a new model to identify unknown counterfactual outcomes for continuous variables.
problem Counterfactual inference for continuous outcomes with strong assumptions.
method Curvature Sensitivity Model to relax assumptions and provide informative bounds.
result Demonstrates effectiveness of the Curvature Sensitivity Model in identifying counterfactual outcomes.
ABCI infers causal models and queries simultaneously using Bayesian active learning.
problem Inference of causal models and effects in a two-stage process is inefficient and unnatural.
method Active Bayesian Causal Inference (ABCI) using Gaussian processes for sequentially designing experiments.
result ABCI is more data-efficient and accurate in learning causal queries from fewer samples.
Generative model improves image realism with word phrase attention.
problem Natural language often involves complex foreground objects and variable background.
method Introduced region-phrase attention between true-grid regions and word phrases.
result Generated more realistic images compared to state-of-the-art algorithms.
New approach considers a buyer with no-regret learning to optimize seller's revenue.
problem Optimizing revenue for a seller selling to a buyer with no-regret learning.
method Analyzes different learning algorithms for the buyer and corresponding optimal auctions for the seller.
result Seller can achieve optimal revenue by setting decreasing reserves over time, surpassing truthful auctions.
ABCD model generates synthetic graphs for community detection with improved scalability and interpretability.
problem Synthetic graphs for community detection are limited in scalability and interpretability.
method Developed a new random graph model (ABCD) with community structure and power-law distribution.
result ABCD model solves scalability and interpretability issues of LFR model.
Fuzzy prediction sets generalize binary predictions to include elements at varying confidence levels.
problem Binary prediction sets are limited; fuzzy prediction sets offer richer guarantees.
method Generalize prediction sets to fuzzy sets, showing they are e-values with merging properties.
result Optimal e-values lead to optimal fuzzy prediction sets, including optimal conformal prediction.
Paper defines predictive multiplicity and measures its severity in classification problems.
problem Challenges in machine learning due to competing models with conflicting predictions.
method Formal measures and integer programming tools for linear classification problems.
result Real-world datasets may admit competing models with wildly conflicting predictions.
A novel continual prediction model outperforms traditional one-time models in predicting AKI.
problem Optimally predicting AKI before it develops during a hospital stay.
method A novel continual prediction model that predicts AKI every time a patient's AKI-relevant variable changes in the EHR.
result The continual prediction model outperformed traditional one-time models, achieving a higher AUC of 0.724 compared to 0.653.
This paper re-examines conformal e-prediction and its advantages over conformal prediction.
problem The relationship between conformal prediction and conformal e-prediction.
method Systematic re-examination of conformal prediction and conformal e-prediction from a modern perspective.
result Conformal e-prediction has advantages such as ease of designing conditional predictors and guaranteed validity of cross-predictors.
Two new methods improve efficiency of conformal predictive systems.
problem Efficiency of conformal predictive systems in regression problems.
method Split conformal predictive systems and cross-conformal predictive systems.
result Cross-conformal predictive systems are more efficient but not guaranteed valid.
Self-calibrating conformal prediction improves interval efficiency and offers a practical alternative.
problem Improving the reliability and uncertainty quantification of machine learning predictions.
method Combines Venn-Abers calibration and conformal prediction for binary and regression problems.
result Improves interval efficiency through model calibration and offers practical alternatives.
The paper aggregates predictions from multiple undisclosed datasets using conformal prediction.
problem Making valid predictions from multiple non-disclosed datasets without data sharing.
method Each dataset uses a transductive conformal predictor independently, and predictions are aggregated.
result The method produces valid and less variable aggregated predictions.
Study uses deep learning to predict asset prices, finds complex target processes lead to meaningless predictions.
problem Complexity of successful price prediction models hinders understanding.
method Deep learning models for high-frequency price prediction, focusing on volatility and directional prediction.
result Inadequately defined target price process renders predictions meaningless.
The paper emphasizes the importance of joint predictions over marginal predictions for decision-making.
problem The need for accurate joint predictions in decision-making problems.
method The paper analyzes combinatorial decision problems, sequential predictions, and multi-armed bandits, introducing an approximate Thompson sampling algorithm and new regret bounds.
result Accurate joint predictions are essential for good performance in decision-making problems.
Behavior modification improves prediction accuracy by nudging user behavior.
problem Improving prediction accuracy using behavior modification techniques.
method Combining prediction and behavior modification with reinforcement learning algorithms.
result Behavior modification can make predictions more certain but may not generalize.
New adaptive conformal predictive systems developed.
problem Severe restrictions on adapting predictive distributions to test objects.
method Calibrating existing predictive systems to ensure full adaptability and validity.
result Developed fully adaptive split-conformal and cross-conformal predictive systems.
Predictions can shape outcomes, study helps predict these effects.
problem Understanding how predictions influence real-world outcomes.
method Causal identifiability analysis of prediction-covariate-outcome relationships.
result Standard supervised learning can identify transferable relationships from predictions.
Proposes feature conformal prediction for broader application in semantic feature spaces.
problem Establishing valid prediction intervals in semantic feature spaces.
method Extends conformal prediction to semantic feature spaces using deep representation learning.
result Feature conformal prediction outperforms regular conformal prediction under mild assumptions.