Enhances GANs with class labels to improve sample quality.
problem Improving sample quality in GANs using class labels.
method Mathematical analysis of GANs with class labels, proposing AM-GAN.
result AM-GAN outperforms other GANs on metrics like Inception Score and AM Score.
ScoreMatchingRiesz improves debiased machine learning and policy effects estimation.
problem Improving debiased machine learning and policy effects estimation.
method Score matching and Riesz representer estimation.
result Estimates policy path for continuous treatments, improving interpretability.
AM converges super-linearly for solving mixed linear regression problems.
problem Learning linear regressors from unlabeled observations in multiple linear regression models.
method Alternating Minimization (AM) algorithm, which alternates between label estimation and regression solving.
result AM converges super-linearly in certain parameter regimes, requiring only O(log log(1/ε)) iterations to achieve an error of ε.
Expanded tribute to Bernard Maskit in Notices of the AMS.
problem None specified in the abstract
method None specified in the abstract
result None specified in the abstract
The spaces of Riemannian metrics on a closed manifold M M M are studied. On the space M {\mathcal M} M of all Riemannian metrics on M M M the various weak Riemannian structures are defined and the corresponding connections are studied. The space A M {\mathcal AM} A M of associated metrics on a symplectic manifold M , ω M,ω M , ω is consider…
COMP-AMS optimizes distributed training with compressed gradients, achieving similar accuracy with less communication.
problem Efficiently training large-scale models in distributed environments with reduced communication costs.
method Distributed optimization framework using gradient averaging and adaptive AMSGrad, with gradient compression and error feedback.
result COMP-AMS achieves the same convergence rate and linear speedup as standard AMSGrad with less communication.
Survey of methods to visualize neural network features.
problem Understanding neural network activation patterns.
method Activation Maximization and Feature Visualization via Optimization.
result Probabilistic interpretation of AM techniques.
This paper improves speech recognition by using raw waveform signals in multi-span CNN acoustic models.
problem Improving speech recognition accuracy using raw waveform signals.
method Proposes a novel multi-span structure for acoustic modelling based on raw waveform signals with multiple CNN input layers.
result Multi-span acoustic models yield a lower word error rate (WER) than traditional FBANK feature-based models.
Updates and rewrites a 1974 AMS Memoir on Lie groups.
problem Real reductive Lie groups and their representations.
method Rewriting and updating a 1974 AMS Memoir.
result Ties with recent approaches to geometric realization of unitary representations.
Deep CNN monitors AM quality with high accuracy.
problem Quality control in AM processes.
method Deep Convolutional Neural Network (CNN) model trained and tested online.
result 94% accuracy and 96% specificity in classifying AM quality.
A new method identifies key dimensions for function analysis.
problem Limitations in Active Subspaces for high-dimensional functions.
method Active Manifolds (AM) method for C 1 ( R m ) C^1(\mathbb{R}^m) C 1 ( R m ) functions. result AM reduces approximation error by an order of magnitude compared to AS.
Real-time machine learning predicts AM process temperatures accurately.
problem Accurate prediction of temperature profiles in AM processes for cost-effective design.
method Ensemble of bagged decision trees (extremely randomized trees) for iterative temperature prediction.
result Mean absolute percentage errors below 1% for temperature profile predictions.
Improved SincNet for better speaker recognition.
problem Speaker recognition challenges and the need for better deep learning models.
method Proposes AM-SincNet, a SincNet-based model with an improved AM-Softmax layer.
result Improved speaker recognition performance, achieving a 40% Frame Error Rate reduction.
Geometrically convex return risk measures on AM-algebras
problem Quantifying risk in time series analysis
method Extending return risk measures to general ordered vector spaces
result Establishing results on finiteness, continuity, separability, and dual and aggregation-based representations
We build an augmentation of the Masur-Minsky marking complex by Groves-Manning combinatorial horoballs to obtain a graph we call the augmented marking complex, A M ( S ) \mathcal{AM}(S) A M ( S ) . Adapting work of Masur-Minsky, we prove that A M ( S ) \mathcal{AM}(S) A M ( S ) is quasiisometric to Teichmüller space with the Teichmüller metric. A similar …
Survey on stability of algebraic varieties and Kahler geometry.
problem Stability of algebraic varieties and Kahler geometry.
method Survey and lecture notes.
result Discussion of recent developments and open problems.
Improved visual speech synthesis using adapted ASR acoustic models.
problem Lack of synchronized audio, video, and depth data for speaker-independent speech-driven visual speech synthesis.
method Adapted an ASR acoustic model trained on audio-only data to the visual speech synthesis domain.
result Viewers significantly prefer animations generated from the adapted ASR acoustic model.
A RL approach optimizes metal AM process parameters for consistent melt pool depth.
problem Optimizing process parameters for metal additive manufacturing to ensure repeatability and control microstructure.
method A Reinforcement Learning (RL) framework based on Q-learning is applied to find optimal laser power and scan velocity combinations.
result The RL framework learns optimal process parameters without prior knowledge, providing a model-free approach.
In this paper, we consider a popular model for collaborative filtering in recommender systems where some users of a website rate some items, such as movies, and the goal is to recover the ratings of some or all of the unrated items of each user. In particular, we consider both the clustering model, where only users (or…
This work develops fast and accurate ROMs for AM models using OL methods.
problem Achieving specific material properties in AM by manipulating process parameters increases computational load.
method Operator learning (OL) approach with Fourier neural operator (FNO) and DeepONet.
result OL methods offer comparable performance and outperform DNN in accuracy and generalizability.
New AM regularization improves both accuracy and robustness.
problem Lack of robustness in deep neural networks.
method Average margin (AM) regularization for margin classifiers or deep neural networks.
result AM regularization can improve both accuracy and robustness to adversarial attacks.
Shai-am simplifies ML for finance, solving code structure and scalability issues.
problem Challenges in integrating ML for investment strategies, including code structure and scalability.
method Integrates a Python framework with modern open-source technologies to manage containerized pipelines and unified interfaces.
result Facilitates collaborative work in quantitative finance by enhancing reusability and readability.
Adaptive Multilevel Splitting improves rare event pricing for financial derivatives.
problem Efficient pricing of binary options in rare event regimes with discontinuous payoffs.
method Adaptive Multilevel Splitting (AMS) reformulates rare-event problem as conditional events.
result AMS achieves up to 200-fold improvements over standard Monte Carlo, preserving unbiasedness.
A new KF handles outliers without MSE loss.
problem Outliers degrade Kalman filter performance.
method NUV priors, EM and AM for variance estimation.
result Outlier-insensitive KF outperforms existing methods.
This work develops a fast-running ROM for MOOSE-based AM model using OL.
problem Achieving desired material properties in real-time manufacturing processes.
method Operator learning (OL) and Fourier neural operator for ROM development.
result OL-based ROM outperforms conventional deep neural network-based ROM in benchmark tests.
Unified framework extends adjoint Schrödinger bridge sampler to discrete spaces.
problem Challenges in learning discrete neural samplers due to gradients and combinatorial complexity.
method Introduces discrete ASBS, a unified framework that extends adjoint Schrödinger bridge sampler to discrete spaces.
result Empirically, discrete ASBS achieves competitive sample quality with significant advantages in training efficiency and scalability.
Paper analyzes agnostic learning of mixed linear regression without generative models.
problem Learning mixed linear regression without assuming stochastic generation.
method Expectation Maximization (EM) and Alternating Minimization (AM) algorithms.
result AM and EM algorithms converge to population loss minimizers under standard conditions.
Automates neural network model selection for efficiency.
problem Efficiently choosing neural network architectures and hyper-parameters.
method Modified micro-genetic algorithm for automated model selection.
result AMS finds efficient neural network models for classification and regression.
New method AM learns optimal vector fields for entire distribution sequences, matching OT.
problem Optimal Transport (OT) problem in generative modeling.
method Action Matching (AM) method learns optimal vector fields for a sequence of distributions.
result AM method achieves optimal transport by learning vector fields for entire distribution sequences.
Defines a new field theory in 1+1+1 dimensions.
problem Developing a new field theory in 1+1+1 dimensions.
method Defines an extended field theory as a quasi 2-functor with values in a completed 2-category, H a m ^ \widehat{\mathcal{H}am} H am . result Extends existing theories and provides a real analog of a construction by Moore and Tachikawa.
New method estimates log-determinant using trace powers, avoiding classical limitations.
problem Estimating log-determinant of large matrices efficiently and accurately.
method Interpolating moment-generating function and its derivative at zero using trace powers.
result No continuous estimator using finite moments can be uniformly accurate over unbounded conditioning.
AM-PPI uses multiple predictors to reduce label cost in healthcare AI.
problem Reduces label cost in post-deployment monitoring of healthcare AI.
method Combines model predictions with a small labeled sample, routing each instance to a cost-appropriate subset of predictors.
result Produces narrower confidence intervals than single-predictor methods.
Proposes AMS-SFE to improve zero-shot learning by aligning semantic feature spaces.
problem Domain shift problem in zero-shot learning due to disjoint seen and unseen data.
method Expands semantic features using an autoencoder and aligns them with visual feature manifold.
result Remarkable performance improvement over existing methods.
Improved robustness in ASR systems with speaker adaptation.
problem Improving robustness in automatic speech recognition systems.
method Weighted-Simple-Add method for adding weighted speaker information vectors to the conformer-based acoustic model.
result Achieved 11% relative improvement in WER on Switchboard 300h Hub5'00 dataset.
Proposes DAM for optimizing discrete generative models.
problem Challenges in optimizing discrete generative models.
method Discrete Adjoint Matching (DAM) for discrete state spaces.
result Demonstrates effectiveness on synthetic and mathematical reasoning tasks.
A scalable system learns acoustic models from 1 Million hours of untranscribed audio.
problem Learning acoustic models from large, untranscribed audio datasets.
method Semi-supervised learning with a student/teacher learning paradigm, focusing on the data and model pipelines.
result Relative accuracy improvements of 10-20% in noisy conditions, with no extensive hyper-parameter tuning.
AMS improves video inference on edge devices by adapting a small model with online knowledge distillation.
problem High computation cost of Deep Neural Networks for real-time video inference on edge devices.
method AMS uses a remote server to continually train and adapt a small model on edge devices, using online knowledge distillation from a large model.
result 0.4--17.8 percent mean Intersection-over-Union improvement in video semantic segmentation.
Survey on foliations and diffeomorphism groups.
problem Relationship between algebraic and homotopical properties.
method Survey and analysis of existing literature.
result Explains the connection between diffeomorphism groups and foliations.
New algorithm optimizes MCMC sampling for structural dynamic models.
problem Time-consuming retraining of neural networks in MCMC methods.
method Adaptive meta-learning SGHMC algorithm that optimizes sampling strategy.
result Trained sampler can be applied to various problems without retraining.
The study connects fairness constraints with optimal transport to derive new insights in classification.
problem Ensuring fairness in classification models without sacrificing performance.
method Using Wasserstein barycenters and optimal transport, the study characterizes optimal classification functions under fairness constraints.
result Maximizing fairness under demographic parity is equivalent to solving a regression problem.
This is an introduction to Taubes's proof of the Weinstein conjecture, written for the AMS Current Events Bulletin. It is intended to be accessible to nonspecialists, so much of the article is devoted to background and context.
AMES framework selects optimal embedding space for latent graph inference.
problem No principled method for choosing the best embedding space for latent graph inference.
method Differentiable AMES framework using backpropagation to select optimal embedding space.
result Consistently achieves comparable or superior results across multiple datasets.
Square Clifford torus uniquely determined by isoperimetric ratio, rectangular torus not.
problem Uniqueness of 3D shape of rectangular Clifford torus based on isoperimetric ratio.
method Closed-form formulas for isoperimetric ratio of stereographic projection, strict monotonicity.
result Isoperimetric ratio does not uniquely determine rectangular Clifford torus shape.
Finding "densely connected clusters" in a graph is in general an important and well studied problem in the literature \cite{Schaeffer}. It has various applications in pattern recognition, social networking and data mining \cite{Duda,Mishra}. Recently, Ames and Vavasis have suggested a novel method for finding cliques i…
The main theorem of the paper shows that a smooth manifold which is homeomorphic to S^2xS^2 and has nonvanishing Ozsvath-Szabo invariant does not admit a perfect Morse function. I am withdrawing the paper because it is unclear to me if such a manifold exists.
New algorithm infers smooth trajectories from unpaired snapshots.
problem Inferring smooth trajectories from unpaired snapshots.
method Lifts interpolation problem to phase space, regresses onto explicit acceleration field.
result Our algorithm is competitive or superior to existing methods on benchmark problems.
This manuscript contains a detailed proof of the Poincare Conjecture. The arguments we present here are expanded versions of the ones given by Perelman in his three preprints posted in 2002 and 2003. This is a revised version taking in account the comments of the referees and others. It has been reformatted in the AMS …
We show that every complete metric space is homeomorphic to the precise locus of zeros of an entire analytic map from a Hilbert space to a Banach space. As a corollary, every complete separable metric space is homeomorphic to the precise locus of zeros of an entire analytic map between two separable complex Hilbert spa…