MAPS and MAPS-SE learn from multiple suboptimal experts to improve policies efficiently.
problem Learning from multiple suboptimal experts in reinforcement learning.
method Active policy improvement from multiple black-box oracles.
result MAPS and MAPS-SE achieve sample efficiency and state-wise imitation learning.
Improved disentanglement in VAEs using aggregated feature maps.
problem Improving disentanglement in Variational Autoencoders (VAEs).
method Regionally aggregated feature maps extracted from pre-trained CNNs on ImageNet.
result 2nd place in NeurIPS 2019 disentanglement challenge.
We continue our study [Ou4] of f-biharmonic maps and f-biharmonic submanifolds by exploring the applications of f-biharmonic maps and the relationships among biharmonicity, f-biharmonicity and conformality of maps between Riemannian manifolds. We are able to characterize harmonic maps and minimal submanifolds by using …
The study improves bounds on pseudo-Anosov maps and certifies minimum and accumulation points of normalized dilatations.
problem Understanding the set of normalized dilatations of fully-punctured pseudo-Anosov maps.
method Improving bounds on the number of tetrahedra in veering triangulations and using computational means.
result Certified that the minimum element of the set of normalized dilatations is μ2 and the minimum accumulation point is μ4. Improves magnetic field mapping using an array of magnetometers with noisy input.
problem Improving magnetic field maps in indoor environments with noisy magnetometer data.
method Uses Gaussian process regression with an array of magnetometers, incorporating known array positions and relative magnetometer locations.
result The method produces higher quality magnetic field maps compared to using a single magnetometer.
Improved Sobolev mappings in Carnot groups with weaker assumptions.
problem Improving Sobolev mappings in Carnot groups with weaker conditions.
method Using Buser-Karcher center-of-mass and polynomial expressions in moments.
result Rigidity and structural results hold under weaker Sobolev exponents.
Improves visualization of high-dimensional data by correcting misleading artifacts in neighbor embedding methods.
problem Misleading visual artifacts in t-SNE and UMAP due to lack of data-independent manifold learning interpretations.
method LOO-map framework that extends embedding maps to the entire input space, identifying and correcting map discontinuities.
result Developed point-wise diagnostic scores to detect unreliable embedding points and improve hyperparameter selection.
Some results of B. Pasynkov and H. Torunczyk on finite-dimensional maps are improved. A generalization of a Dranishnikov-Uspenskij theorem about extensional dimension is also obtained.
Improved Yang-Yau inequality for all orientable surfaces except for specific genera.
problem Bounding the first eigenvalue of the Laplacian on orientable surfaces.
method Using holomorphic maps to CP^n to improve the Yang-Yau inequality.
result Quantitative improvement of the Yang-Yau inequality for all genera except 4, 6, 8, 10, and 14.
An ODE variational calculation shows that an image principle curvature ratio factor can raise the lower bound, 2(Image Area), on energy of a harmonic map of a surface into Rn. In certain situations, including all radially symmetry harmonic maps, equality is achieved.
Improve exposition and explain metric bundle equivalence.
problem Improving exposition and explaining metric bundle equivalence.
method Improved exposition and appendix explaining equivalence of flaring conditions.
result Equivalence of flaring conditions explained.
In this note, we generalize biharmonic equation for rotationally symmetric maps ([4], [16], [10]) to equivariant maps between model spaces and use it to give a complete classification of rotationally symmetric conformal biharmonic maps from a 4-dimensional space form into a 4-dimensional model space. We also give a…
Improved disentanglement through learned feature aggregation.
problem Disentangling latent factors in images.
method Variational autoencoder trained on regionally aggregated feature maps from ImageNet.
result 2nd place in NeurIPS 2019 disentanglement challenge.
Riemannian Neural OT maps improve scalability on manifolds.
problem Challenges in extending neural OT to high-dimensional Riemannian manifolds.
method Introduces Riemannian Neural OT (RNOT) maps that avoid discretization and incorporate geometric structure.
result RNOT maps approximate Riemannian OT maps with sub-exponential complexity in the dimension.
Framework improves ML flood mapping generalization.
problem Improving machine learning models' ability to generalize to new conditions.
method Dimensionless, multi-scale features constrained by the Buckingham Π theorem.
result Model outperformed dimensional features, improving AUC in unmapped areas.
New method improves interpretability of fMRI decoding models.
problem Uninterpretable deep neural networks in fMRI decoding.
method Adversarial training to make DNNs robust to noise and improved saliency map methods.
result Saliency maps from adversarial-trained DNNs are more interpretable than those from other methods.
Neumann eigenmaps improve landmark-based diffusion map embeddings.
problem Landmark-based diffusion map embeddings can be computationally inefficient and unstable.
method NeuMaps use a renormalized Neumann Laplacian for eigendecomposition, incorporating landmarks as a subgraph.
result NeuMaps offer a computationally efficient and stable embedding method.
Two elements generate all mappings of a nonorientable surface.
problem Generating the mapping class group of a nonorientable surface.
method Proving two elements generate the mapping class group for g≥13. result The mapping class group of a nonorientable surface of genus g≥13 can be generated by exactly two elements. Improved diffusion map enhances manifold regularization for semi-supervised learning.
problem Limited performance of manifold regularization models in capturing global structure.
method Enhanced diffusion map with improved label propagation function.
result Proposed method improves manifold regularization model's performance.
Method uses aggregate crop statistics to improve satellite-based crop type mapping.
problem Limited field-level crop labels for training satellite-based maps.
method Corrects classifier by accounting for shifts in crop type composition and feature means.
result Substantial improvements in overall classification accuracy, reducing misclassifications by 21.9% on average.
This paper addresses a boosting method for mapping functionality of neural networks in visual recognition such as image classification and face recognition. We present reversible learning for generating and learning latent features using the network itself. By generating latent features corresponding to hard samples an…
Proposes m-POT to improve m-OT's misspecified mappings issue.
problem Misspecified mappings in mini-batch optimal transport.
method Partial optimal transport (POT) between mini-batch empirical measures.
result m-POT alleviates incorrect mappings compared to current methods.
Enhances stability ranges for Torelli and congruence subgroup homologies.
problem Improving stability ranges for specific subgroup homologies.
method Analyzes H2(Torelli subgroup of Aut(Fn)'s), H2(Torelli subgroup of mapping class groups), and Hk(congruence subgroups of GL_n(R)'s).
result Improved central stability ranges for various subgroup homologies.
Improved spatial distribution learning with Bayesian transport maps and parametric shrinkage.
problem Learning non-Gaussian spatial distributions with limited training data.
method Proposed ShrinkTM approach using Bayesian transport maps with parametric shrinkage.
result ShrinkTM outperforms existing BTM, especially with few training samples.
New method improves matrix completion with functional maps.
problem Matrix completion with geometric structure.
method Functional map regularization for geometric matrix completion.
result Significant performance improvement over state-of-the-art methods.
Paper proves uniqueness of minimal maps in curved spaces.
problem Proving uniqueness of minimal maps into Cartan-Hadamard manifolds.
method Proof based on convexity of functions in terms of squared singular values.
result Uniqueness theorem for minimal maps into Riemannian manifolds.
MAP inference for general energy functions remains a challenging problem. While most efforts are channeled towards improving the linear programming (LP) based relaxation, this work is motivated by the quadratic programming (QP) relaxation. We propose a novel MAP relaxation that penalizes the Kullback-Leibler divergence…
Visualizes DNNs using topographic maps for better understanding.
problem Difficulty in understanding how DNNs solve tasks.
method Adapting neuroscience methods to visualize DNN activations.
result Improved transparency and interpretability of DNN-based systems.
Improved spectral convergence bounds for diffusion maps on tori.
problem Weak theoretical error bounds for diffusion maps.
method Spatial Hardy space estimates, PDE spectral stability, Sinkhorn weights.
result Matched pointwise error bounds for spectral data and operator convergence.
Improved CG force-field learning from all-atom data.
problem Training accurate coarse-grained models from all-atom simulations is challenging.
method Optimized force mapping to improve statistical efficiency of force-field learning.
result Substantially improved CG force-fields can be learned from the same simulation data.
We show that every cross ratio preserving homeomorphism between boundaries of Hadamard manifolds extends to a continuous map, called circumcenter extension, provided that the manifolds satisfy certain visibility conditions. We show that this map is a rough isometry, whenever the manifolds admit cocompact group actions …
This paper proposes a new method for an optimized mapping of temporal variables, describing a temporal stream data, into the recently proposed NeuCube spiking neural network architecture. This optimized mapping extends the use of the NeuCube, which was initially designed for spatiotemporal brain data, to work on arbitr…
The paper improves Zakalyukin's lemma for frontals and applies it to surface singularities.
problem Improving the conditions under which wave front germs imply map germs.
method Generalization of Zakalyukin's lemma for frontals and applications to surface singularities.
result The paper provides a more general version of Zakalyukin's lemma for map germs.
New translation equivariant neural processes improve spatio-temporal data modeling.
problem Improving posterior prediction maps for spatio-temporal data.
method Introduced translation equivariant transformers within neural processes.
result TE-TNPs outperform non-equivariant TNPs and other baselines.
Improves QMC for complex distributions using transport maps.
problem Challenges in applying QMC to general target distributions.
method Train a transport map to approximate target distributions, ensuring RQMC achieves superior error rates.
result Transport QMC achieves faster convergence rates than standard Monte Carlo under mild conditions.
Improved anti-cancer drug sensitivity prediction using REFINED CNN ensemble learning.
problem Challenges in predicting anti-cancer drug sensitivity for individual cell lines.
method Using REFINED CNN, which represents high-dimensional vectors as compact 2D images with spatial correlations, and building ensembles of these models.
result Ensemble approaches significantly improve drug sensitivity prediction performance compared to single models.
We present a global optimization approach for solving the maximum a-posteriori (MAP) clustering problem under the Gaussian mixture model.Our approach can accommodate side constraints and it preserves the combinatorial structure of the MAP clustering problem by formulating it asa mixed-integer nonlinear optimization pro…
Improved EXACT strategy reduces GNN memory consumption and runtime.
problem Efficiently training large-scale GNNs with reduced memory usage.
method Block-wise quantization of intermediate activation maps with improved variance minimization.
result Further reduction in memory consumption (>15%) and runtime speedup (5%) with similar performance trade-offs.
Improved Liouville theorems for ancient solutions to V-harmonic map heat flows.
problem Establishing Liouville theorems for ancient solutions to V-harmonic map heat flows.
method Refined gradient estimates and exponential growth conditions.
result Better Liouville theorems for ancient solutions to V-harmonic map heat flows.
CAM-GAN improves GANs for continual learning with efficient feature map transformations.
problem Efficient continual learning for GANs with reduced parameter growth.
method Designing and leveraging parameter-efficient feature map transformations, including global and task-specific parameters, residual bias, and Fisher information matrix.
result Significantly improved model performance and high-quality samples with fewer parameters.
MAP-Elites generates diverse trading strategies for improved execution performance.
problem Optimizing trading execution schedules in volatile market conditions.
method Quality-diversity algorithm (MAP-Elites) generating a portfolio of specialized strategies.
result Diverse strategies achieve 8-10% performance improvements, validating quality-diversity methods.
Paper improves SOMs for non-Euclidean data modeling.
problem Traditional SOMs assume Euclidean data, limiting their applicability.
method Introduces topology-related extensions to traditional SOM algorithm.
result Improves SOMs for non-Euclidean data, enhancing data modeling.
Enhances graph classification models on small datasets.
problem Over-fitting and undergeneralization on small-scale benchmark datasets.
method Data augmentation via graph structure transformation and model evolution framework.
result Average improvement of 3 - 13% accuracy on graph classification tasks.
Improves machine learning models by incorporating physical laws into feature maps.
problem Lack of model interpretability in classical machine learning approaches.
method Physics-informed feature maps constructed from physical laws and dimensional analysis.
result Enhanced model interpretability and potential discovery of new physical equations.
Note on minimal maps' uniqueness via singular values.
problem Uniqueness of minimal maps into \(\mathbb{R}^n\).
method Using singular values and convexity of area functional, proving local linearity of singular value vectors.
result Improved uniqueness theorem for minimal graphs.
The paper explores dual learning, a technique that improves machine translation and image transformation.
problem Understanding and improving dual learning's effectiveness and conditions.
method Theoretical analysis and algorithmic extension of dual learning.
result Multi-step dual learning boosts performance under mild conditions.
We estimate the dimensions of the spaces of holomorphic sections of certain line bundles to give improved lower bounds on the index of complex isotropic harmonic maps to complex projective space from the sphere and torus, and in some cases from higher genus surfaces.
In 1996, Shi generalized the epsilon-regularity theorem of Schoen and Uhlenbeck to energy-minimizing harmonic maps from a domain equipped with a bounded measurable Riemannian metric. In the present work we prove a compactness result for such energy-minimizing maps. As an application, we combine our result with Shi's th…