Lecture notes on spectral graph methods at UC Berkeley.
problem No specific problem stated in the abstract.
method Lecture notes based on teaching spectral graph methods.
result No specific key result mentioned in the abstract.
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
169,341 papers · 148 categories
Trend · papers per month
44 results for “UC Berkeley”
Lecture notes on using randomness in linear algebra.
problem Efficiently solving large linear algebra problems.
method Randomized algorithms for linear algebra tasks.
result Demonstrated practical applications of randomized linear algebra.
The paper tackles multi-agent inverse reinforcement learning in stochastic games, proposing solutions for five variants.
problem Inverse reinforcement learning in multi-agent stochastic games with different solution concepts.
method Developed novel approaches for five variants of multi-agent inverse reinforcement learning (MIRL) in a two-player general-sum stochastic game framework.
result Proposed solutions for five variants of MIRL: uCS-MIRL, advE-MIRL, cooE-MIRL, uCE-MIRL, and uNE-MIRL.
If Gamma is any finite graph, then the unlabelled configuration space of n points on Gamma, denoted UC^n(Gamma), is the space of n-element subsets of Gamma. The braid group of Gamma on n strands is the fundamental group of UC^n(Gamma). We apply a discrete version of Morse theory to these UC^n(Gamma), for any n and any …
New groups derived from square configurations have right-angled and HNN structures.
problem Understanding the fundamental groups of square configurations and their homotopy properties.
method Analyzing configuration spaces and their fundamental groups, proving group presentations and homotopy equivalences.
result The fundamental groups of certain square configurations have minimal presentations with commutator relators and are HNN extensions of specific meta-square groups.
The paper calibrates uncertainty in dropout variational inference models.
problem Miscalibration of model uncertainty in dropout variational inference.
method Logit scaling methods are extended to recalibrate model uncertainty.
result Logit scaling reduces miscalibration, improving reliability of predictions.
A new solar forecasting method uses clustering and machine learning to improve accuracy.
problem Improving solar forecasting accuracy through weather conditions.
method Unsupervised clustering, pattern recognition, and multi-model machine learning.
result UC-based models outperform non-UC models by approximately 20%.
UC-SSP algorithm tackles exploration in stochastic shortest path problems without loop-free assumption.
problem Exploration in goal-oriented reinforcement learning problems under stochastic shortest path formulation.
method UC-SSP algorithm with a novel stopping rule to interrupt and switch policies.
result Regret bound of after episodes.
Proposes multi-neighborhood LBPs for land use classification.
problem Challenges in classifying land use images due to intra class variability and inter class similarities.
method Uses multi-neighborhood LBPs combined with nearest neighbor classifier.
result Achieved an accuracy of 77.76% on UC Merced 21 class land use image dataset.
Statistical tests for fairness in admissions data reveal hidden patterns.
problem Simpson's paradox in admissions data hides true gender bias.
method Introduces a new statistical test based on Pearl's instrumental-variable inequalities.
result Statistical tests for fairness coincide with causal notions for the Berkeley admissions case.
Thesis on surgery on paracompact manifolds.
problem Surgery on paracompact manifolds.
method Not specified in the abstract.
result Not specified in the abstract.
This paper calibrates uncertainty in dropout variational inference models.
problem Uncertainty in variational inference with dropout is poorly calibrated.
method Temperature scaling is extended to dropout variational inference.
result Temperature scaling reduces miscalibration of uncertainty.
Optimization techniques for machine learning explained.
problem Improving machine learning models' performance.
method Course notes and tutorials on optimization methods.
result Comprehensive coverage of optimization techniques.
This is an extended version of a talk given at the conference "Algebra and Topology in Interaction" on the occasion of the 70th Anniversary of D.B. Fuchs at UC Davis in September 2009. It is a brief survey of an area originated around 1995 by I. Gelfand and the author.
Improvements on Uncertainty Quantification for Node Classification via Distance-Based Regularizationcs.LG
The paper improves uncertainty quantification for node classification using distance-based regularization.
problem Uncertainty in deep learning models, especially for node classification tasks.
method Graph posterior networks (GPNs) with UCE loss function, followed by a distance-based regularization.
result The proposed distance-based regularization outperforms state-of-the-art methods in OOD detection and misclassification detection.
Sz\H ucs proved in 2000 that the -tuple-point manifold of a generic immersion is cobordant to the -point manifold of its generic projection. Here we slightly extend this by showing that the natural mappings of these manifolds are bordant to each other. The main novelty of our approach is that we constru…
Paper accelerates K-means clustering for large sparse document data.
problem Efficiently clustering large-scale sparse document data.
method Designs an AFM algorithm leveraging UCs and inverted-index structure.
result Significantly improves clustering speed for large-scale documents.
Proposes ESCFR to estimate treatment effects from biased data.
problem Treatment selection bias in observational data.
method Stochastic optimal transport with relaxed mass-preserving and proximal factual outcome regularizers.
result Significantly better performance in estimating treatment effects.
In May 2015, a conference entitled "Groups, Geometry, and 3-manifolds" was held at the University of California, Berkeley. The organizers asked participants to suggest problems and open questions, related in some way to the subject of the conference. These have been collected here, roughly divided by topic. The name (o…
This paper improves multi-label classification by leveraging high-order label correlations.
problem Improving accuracy in multi-label classification tasks using label correlations.
method Exploiting high-order label correlations through a supervised learning classifier system (UCS) and label powerset (LP) strategy.
result The proposed method outperforms other LP-based methods on multiple benchmark datasets.
In these notes, I will sketch a new approach to Khovanov homology of knots and links based on counting the solutions of certain elliptic partial differential equations in four and five dimensions. The equations are formulated on four and five-dimensional manifolds with boundary, with a rather subtle boundary condition …
Donor-aware scRNA-seq benchmarks improve classification accuracy in inflammatory bowel disease.
problem Influenza disease classification from scRNA-seq data is prone to donor-level confounding.
method Developed and evaluated three feature representations across two IBD cohorts.
result Compartment-stratified CLR composition and GatedStructuralCFN embeddings outperform linear models in classification accuracy.
Adversarial attacks degrade neural network policies in reinforcement learning.
problem Adversarial attacks on neural network policies in reinforcement learning.
method Existing adversarial example crafting techniques used.
result Significant drop in performance with small perturbations.
State-only imitation learning improves dexterous manipulation learning from videos.
problem High sample complexity in complex domains like dexterous manipulation.
method Train an inverse dynamics model to predict actions from states and train the policy jointly.
result Performs on par with state-action approaches and outperforms RL alone.
Hierarchical decoupling improves sample efficiency for complex robots.
problem Learning long-range behaviors on complex robots.
method Two-part policy: low-level imitation and high-level transfer, with KL regularization.
result Hierarchical transfer significantly improves zero-shot high-level transfer and stabilizes learning.
Dynamic steerable blocks improve deep networks by learning filter invariances.
problem Pixel-based filters ignore image properties, leading to suboptimal performance.
method Developed frame-based ResNets and Densenets, which are steerable under predefined transformations.
result Dynamic steerable blocks outperform other approaches on contour detection datasets.
Sparse symmetric tensor regression reduces brain connectivity complexity.
problem Complex brain connectivity analysis in neuroimaging.
method Sparse symmetric tensor regression model for functional connectivity.
result Superior performance in Alzheimer's disease detection.
Neural regression predicts surgery durations with reduced overbooking.
problem Uncertainty in surgery durations and scheduling inefficiencies.
method Neural heteroscedastic regression models to estimate surgery durations and uncertainty.
result Improved scheduling strategies with 20% reduction in overbooking.
CARL safely adapts RL agents for safety-critical tasks.
problem Safety hazards in RL for safety-critical tasks.
method CARL combines model-based RL and cautious adaptation.
result CARL achieves higher rewards with fewer failures in safety-critical tasks.
A framework uses complex networks for image segmentation.
problem Over-segmentation in image segmentation.
method Initial segmentation, adaptive network construction, community detection.
result The proposed framework improves segmentation performance.
A new framework for spectral clustering over distributed data with minimal communication.
problem Efficiently computing spectral clustering over data distributed across multiple sites.
method Local parallel computing at data locations, enabling distributed data to be a benefit.
result Achieves almost no loss in accuracy with negligible communication overhead and substantial speedup.
This paper gives a leisurely introduction to Calabi-Yau manifolds and special Lagrangian submanifolds from the differential geometric point of view, followed by a survey of recent results on singularities of special Lagrangian submanifolds, and their application to the SYZ Conjecture. It is aimed at graduate students i…
Visual analytics system for comparing medical records using sequence embeddings.
problem Challenges in analyzing medical records due to high dimensionality, irregularity, and sparsity.
method Event and sequence embeddings using autoencoder and self-attention mechanism, with sequence alignment for comparison.
result Demonstrated effectiveness with real-world neonatal ICU dataset.
Improved cooperation between levels boosts reinforcement learning performance.
problem Training multi-level policies in hierarchical reinforcement learning.
method Modeling policy optimization as a multi-agent process and inducing cooperation between sub-policies.
result Inducing cooperation between sub-policies leads to stronger and more sample-efficient policies.
NGE uses neural graphs to efficiently design robots.
problem Designing robots is hard due to combinatorial search space and evaluation costs.
method Formulated as graph search, NGE uses neural networks for policy parameterization and graph mutation with uncertainty.
result NGE significantly outperforms previous methods, discovering kinematically preferred structures.
SUPE combines unlabeled data with RL to efficiently explore tasks.
problem Efficient exploration in reinforcement learning with sparse rewards.
method Extract low-level skills using VAE, pseudo-label unlabeled data, and use as off-policy data for online RL.
result SUPE outperforms prior methods across 42 long-horizon tasks.
New algorithms achieve no-regret learning even with adversarial transitions and losses.
problem No-regret learning impossible with adversarial transitions and losses.
method Developed algorithms for adversarial Markov Decision Processes with smooth regret increase.
result Achieved regret, with measuring adversarial transition function.
CRATE-MAE learns structured representations from unlabeled data.
problem Learning structured representations from unlabeled data.
method Structured Diffusion with White-Box Transformers.
result CRATE-MAE achieves highly promising performance on large-scale imagery datasets.
Framework analyzes leaf vein architecture using deep learning and statistical methods.
problem Discards structural information in leaf venation studies.
method Integrates deep learning and statistical techniques to represent and analyze leaf vascular architecture.
result Identifies significant gene-environment interactions in leaf vascular architecture.
ReduNet optimizes data compression by maximizing rate reduction in deep networks.
problem Optimizing deep networks for high-dimensional multi-class data.
method Maximizing rate reduction through iterative gradient ascent, leading to a multi-layer deep network.
result ReduNet achieves optimal linear discriminative representation and is more efficient in the spectral domain.
Human Action Recognition Using Deep Multilevel Multimodal (M2) Fusion of Depth and Inertial Sensorscs.LG
New deep fusion methods improve human action recognition using depth and inertial sensor data.
problem Existing multimodal HAR frameworks lack mid-level feature fusion.
method Proposes three deep multilevel multimodal fusion frameworks, transforming depth and inertial sensor data into images and using convolution with Prewitt filter to create modality within modality.
result Supremacy of proposed fusion frameworks over existing methods on three publicly available datasets.
DisCor corrects reinforcement learning issues by re-weighting collected data.
problem Reinforcement learning algorithms struggle with instability and sensitivity to hyperparameters.
method DisCor reweights collected data to mitigate issues caused by the distribution of experience.
result DisCor improves reinforcement learning in challenging settings like multi-task learning and noisy reward signals.
Project aims to improve robot vision by adapting to new environments.
problem Robots struggle to recognize objects in new settings.
method Selected and evaluated state-of-the-art DA methods on various datasets.
result Training a good object classifier remains challenging.
TMLE improves unbiased estimation in public health studies.
problem Improving unbiased estimation in observational studies.
method Targeted Maximum Likelihood Estimation (TMLE) integrates machine learning and statistical theory.
result TMLE has been adopted by researchers worldwide, especially outside the US.