In this paper, we propose a dual memory structure for reinforcement learning algorithms with replay memory. The dual memory consists of a main memory that stores various data and a cache memory that manages the data and trains the reinforcement learning agent efficiently. Experimental results show that the dual memory …
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.
168,695 papers · 148 categories
Trend · papers per month
48 results for “Dual training”
Many supervised learning tasks are emerged in dual forms, e.g., English-to-French translation vs. French-to-English translation, speech recognition vs. text to speech, and image classification vs. image generation. Two dual tasks have intrinsic connections with each other due to the probabilistic correlation between th…
We present a dual subspace ascent algorithm for support vector machine training that respects a budget constraint limiting the number of support vectors. Budget methods are effective for reducing the training time of kernel SVM while retaining high accuracy. To date, budget training is available only for primal (SGD-ba…
Dual training method for EBMs with overparametrized neural networks.
problem Training EBMs with non-convex energies is challenging.
method Derive variational principles and dual GDA algorithm for feature-learning regime.
result Dual GDA algorithm performs best with similar time scales for features and particles.
Study finds no evidence dual-class stocks are effective predictors.
problem Investment efficiency of dual-class stocks.
method In-depth analysis of stock price divergence, innovative LSTM model training set selection.
result No compelling evidence dual-class stocks are effective predictors.
Semi-supervised wrapper methods are concerned with building effective supervised classifiers from partially labeled data. Though previous works have succeeded in some fields, it is still difficult to apply semi-supervised wrapper methods to practice because the assumptions those methods rely on tend to be unrealistic i…
A fast method for training linear classifiers maximizes margins.
problem Training linear classifiers with maximum margins.
method Momentum-based gradient method derived from convex dual with Nesterov acceleration.
result Exponentially faster convergence rate compared to standard methods.
We relate the minimax game of generative adversarial networks (GANs) to finding the saddle points of the Lagrangian function for a convex optimization problem, where the discriminator outputs and the distribution of generator outputs play the roles of primal variables and dual variables, respectively. This formulation …
Dual-objective GANs reduce training instabilities with tunable α-loss parameters.
problem Training instabilities in Generative Adversarial Networks (GANs).
method Introduce -GANs with dual objectives modeled using -loss.
result Upper bounds on estimation error show improved performance under certain conditions.
Binarization of digital documents is the task of classifying each pixel in an image of the document as belonging to the background (parchment/paper) or foreground (text/ink). Historical documents are often subjected to degradations, that make the task challenging. In the current work a deep neural network architecture …
New method trains normalizing flows using entropy-regularized transport.
problem Training continuous normalizing flows efficiently.
method Formulates flows as gradients of scalar potentials, training only these potentials.
result Trains normalizing flows without explicit flow computation during training.
DPTA improves CIL by adapting PTMs with dual prototypes.
problem Catastrophic forgetting in incremental learning with pre-trained models.
method Dual-Prototype Network with Task-wise Adaptation (DPTA).
result DPTA consistently outperforms recent methods by 1\%-5\% on multiple benchmarks.
This paper introduces and evaluates a novel training method for neural networks: Dual Variable Learning Rates (DVLR). Building on insights from behavioral psychology, the dual learning rates are used to emphasize correct and incorrect responses differently, thereby making the feedback to the network more specific. Furt…
DFM simplifies CNF training without interpolants.
problem Efficiently training CNFs with computationally expensive ODE solving.
method DFM optimizes dual vector fields for bijective transformations.
result DFM outperforms CNF trained with FM or ML objectives.
Constrained Markov Decision Process (CMDP) is a natural framework for reinforcement learning tasks with safety constraints, where agents learn a policy that maximizes the long-term reward while satisfying the constraints on the long-term cost. A canonical approach for solving CMDPs is the primal-dual method which updat…
Convex dual network improves neural network reconstruction for medical imaging.
problem Non-convex nature of neural networks hinders their use in sensitive applications.
method Introduces a convex duality framework for a two-layer fully-convolutional ReLU denoising network.
result Training neural networks with weight decay regularization induces path sparsity and piecewise linear filtering.
The paper optimizes training samples for image denoising across different noise levels.
problem Training a denoiser for all noise levels with uniform sample distribution.
method Derives a dual ascent algorithm for optimal sampling distribution.
result The algorithm converges to an optimal sampling distribution for deep neural networks.
Radial Basis Functions Neural Networks (RBFNNs) are tools widely used in regression problems. One of their principal drawbacks is that the formulation corresponding to the training with the supervision of both the centers and the weights is a highly non-convex optimization problem, which leads to some fundamentally dif…
In modern large-scale machine learning applications, the training data are often partitioned and stored on multiple machines. It is customary to employ the "data parallelism" approach, where the aggregated training loss is minimized without moving data across machines. In this paper, we introduce a novel distributed du…
A new method trains physics-constrained neural networks more efficiently.
problem Training machine learning tools with limited data and physical constraints.
method Dual-Dimer method for searching saddle points in nonconvex-nonconcave functions.
result The Dual-Dimer method improves training efficiency and convergence speed.
(Martingale) Optimal Transport And Anomaly Detection With Neural Networks: A Primal-dual Algorithmmath.OC
In this paper, we introduce a primal-dual algorithm for solving (martingale) optimal transportation problems, with cost functions satisfying the twist condition, close to the one that has been used recently for training generative adversarial networks. As some additional applications, we consider anomaly detection and …
We develop a general duality between neural networks and compositional kernels, striving towards a better understanding of deep learning. We show that initial representations generated by common random initializations are sufficiently rich to express all functions in the dual kernel space. Hence, though the training ob…
Dual explanation method using convex hulls and example-based vectors.
problem Local and global explanation of complex models.
method Dual representation of instances as convex combinations, generating new dual dataset, training linear surrogate model, computing feature importance.
result Effective example-based and local/global explanation of complex models.
Dual-ISL improves implicit generative model training with convex optimization and explicit density approximation.
problem Training implicit generative models with robust and practical likelihood-free objectives.
method Introduces dual-ISL, a novel likelihood-free objective using a convex divergence derived from the invariant statistical loss (ISL) framework.
result Dual-ISL yields a convex optimization problem in the space of model densities, providing explicit density approximation and improved training stability.
This paper considers the design of optimal resource allocation policies in wireless communication systems which are generically modeled as a functional optimization problem with stochastic constraints. These optimization problems have the structure of a learning problem in which the statistical loss appears as a constr…
Proposes a fair meta-learning framework for few-shot classification.
problem Fairness in few-shot learning.
method Primal-Dual subgradient approach for fair initialization.
result Significant improvements over prior work in fairness.
Proposes a link between randomness and compression in deep learning.
problem Improving efficiency in deep learning training.
method Introduces a novel tomographic compression framework called Dual Tomographic Compression (DTC).
result Demonstrates high correlation between learning performance and Gibbs entropy over compression ratios.
The Information Autoencoding Family: A Lagrangian Perspective on Latent Variable Generative Modelsstat.ML
A large number of objectives have been proposed to train latent variable generative models. We show that many of them are Lagrangian dual functions of the same primal optimization problem. The primal problem optimizes the mutual information between latent and visible variables, subject to the constraints of accurately …
Dualing GANscs.LG
Generative adversarial nets (GANs) are a promising technique for modeling a distribution from samples. It is however well known that GAN training suffers from instability due to the nature of its maximin formulation. In this paper, we explore ways to tackle the instability problem by dualizing the discriminator. We sta…
A new method for distributed optimization reduces communication rounds without minibatches.
problem Efficient training in distributed machine learning with different data distributions.
method A primal-dual method (GA-MSGD) applied to the Lagrangian of distributed optimization.
result Achieves linear convergence in communication rounds for strongly convex objectives.
This work investigates the training of conditional random fields (CRFs) via the stochastic dual coordinate ascent (SDCA) algorithm of Shalev-Shwartz and Zhang (2016). SDCA enjoys a linear convergence rate and a strong empirical performance for binary classification problems. However, it has never been used to train CRF…
The paper analyzes how GANs converge using dual metric flows.
problem Understanding the convergence dynamics of GANs.
method Investigates the convergence of GANs using dual metric flows, formal definitions, and proving convergence.
result GAN learning dynamics converge to a limit when learning rate is small.
DCCNNs reduce computational overhead and ambiguity in convolutional neural networks.
problem Reducing computational overhead and ambiguity in convolutional neural networks.
method Introducing a primal learning problem and constructing a dual convex training program, using Fenchel conjugates and Karush-Kuhn-Tucker conditions.
result Eliminates ambiguity and reduces computational overhead in constructing a large kernel matrix.
We propose a voted dual averaging method for online classification problems with explicit regularization. This method employs the update rule of the regularized dual averaging (RDA) method, but only on the subsequence of training examples where a classification error is made. We derive a bound on the number of mistakes…
MDA optimizer performs similarly to SGD+M in CV and Adam in NLP.
problem Performance degradation due to choosing the wrong optimizer.
method Modernized Dual Averaging (MDA) optimizer, inspired by dual averaging.
result MDA performs as well as SGD+M in CV and as Adam in NLP.
FairDTD improves fairness in GNNs by distilling dual teacher knowledge, balancing utility and bias.
problem Bias in GNN predictions due to sensitive attributes.
method Dual-Teacher Distillation with a causal graph model, feature and structure teachers, and graph-level distillation.
result Achieves optimal fairness while preserving high model utility.
Proposes TgNN-LD to improve neural network effectiveness and efficiency.
problem Limits in maintaining tradeoff between data and domain knowledge.
method Converts loss function to constrained form with PDEs, ECs, and EK as constraints, incorporating Lagrangian variables for equitable tradeoff.
result Improves prediction accuracy and conserves resources.
A new method reduces feature size in CRFs for faster training.
problem Challenges in solving sparse CRFs for large-scale applications.
method Safe dynamic screening method exploiting dual optimum estimation.
result Significant speedup in training CRFs without loss of accuracy.
New method tackles composite optimization with error feedback.
problem Challenges in distributed machine learning training and message compression.
method Combines Dual Averaging with EControl for composite optimization.
result First strong convergence analysis for composite optimization with error feedback.
Dual-track model generates classical piano music better than other methods.
problem Generating inter-dependent piano music.
method Dual-track architecture with various neural network models and music representations.
result Proposed model outperforms other methods in evaluation.
GPs with neural network dual kernels improve reinforcement learning performance.
problem Combining the strengths of DNNs and GPs for reinforcement learning.
method Apply GPs with neural network dual kernels to solve reinforcement learning tasks.
result GPs with neural network dual kernels perform at least as well as conventional methods on the mountain-car problem.
Uniform sampling of training data has been commonly used in traditional stochastic optimization algorithms such as Proximal Stochastic Gradient Descent (prox-SGD) and Proximal Stochastic Dual Coordinate Ascent (prox-SDCA). Although uniform sampling can guarantee that the sampled stochastic quantity is an unbiased estim…
Primal-Dual Wasserstein GANstat.ML
We introduce Primal-Dual Wasserstein GAN, a new learning algorithm for building latent variable models of the data distribution based on the primal and the dual formulations of the optimal transport (OT) problem. We utilize the primal formulation to learn a flexible inference mechanism and to create an optimal approxim…
Interpretable neural model for few-shot time-series classification.
problem Few-shot time-series classification challenges.
method Dual Prototypical Shapelet Networks (DPSN) framework.
result DPSN framework outperforms state-of-the-art methods, especially with limited data.
In this paper, we present a reverberation removal approach for speaker verification, utilizing dual-label deep neural networks (DNNs). The networks perform feature mapping between the spectral features of reverberant and clean speech. Long short term memory recurrent neural networks (LSTMs) are trained to map corrupted…
How to generate human like response is one of the most challenging tasks for artificial intelligence. In a real application, after reading the same post different people might write responses with positive or negative sentiment according to their own experiences and attitudes. To simulate this procedure, we propose a s…
Paper tackles robust model training with a new stochastic algorithm.
problem Training robust models against data distribution shift.
method Derives a novel dual formulation and proposes a nested stochastic gradient descent algorithm.
result Establishes polynomial iteration and sample complexities for large-scale DRO problems.
This paper shows that the implicit bias of gradient descent on linearly separable data is exactly characterized by the optimal solution of a dual optimization problem given by a smoothed margin, even for general losses. This is in contrast to prior results, which are often tailored to exponentially-tailed losses. For t…