arXiv research

Paper proves multiplicative weight updates can train neural networks without learning rate tuning.

New algorithm for online optimization over symmetric cones, unifying previous methods.

Online learning makes sequence of decisions with partial data arrival where next movement of data is unknown. In this paper, we have presented a new technique as multiple times weight updating that update the weight iteratively forsame instance. The proposed technique analyzed with popular state-of-art algorithms from …

New algorithm provably converges to second-order stationary points in NMF.

Algorithm learns Sherrington-Kirkpatrick model parameters at low temperatures.

Paper proposes efficient weight updates for edge nodes with minimal communication.

A model for deciding which facts to remember in a lifelong learning scenario.

New algorithm uses PSO to optimize DNN training parameters in distributed systems.

In this paper, we provide a novel construction of the linear-sized spectral sparsifiers of Batson, Spielman and Srivastava [BSS14]. While previous constructions required $Ω(n^4)$ running time [BSS14, Zou12], our sparsification routine can be implemented in almost-quadratic running time $O(n^{2+\varepsilon})$. The funda…

We show that deep networks can be trained using Hebbian updates yielding similar performance to ordinary back-propagation on challenging image datasets. To overcome the unrealistic symmetry in connections between layers, implicit in back-propagation, the feedback weights are separate from the feedforward weights. The f…

In this paper, we present a novel approach for fine-tuning a decoder-side neural network in the context of image compression, such that the weight-updates are better compressible. At encoder side, we fine-tune a pre-trained artifact removal network on target data by using a compression objective applied on the weight-u…

Study shows memory needs grow with task sequence length in continual learning.

Regression problems that have closed-form solutions are well understood and can be easily implemented when the dataset is small enough to be all loaded into the RAM. Challenges arise when data is too big to be stored in RAM to compute the closed form solutions. Many techniques were proposed to overcome or alleviate the…

Improved MMWU algorithm achieves instance-optimal regret bound for matrix LEA.

RSO uses random weight perturbations to train deep networks without gradients.

We describe $k$-MLE, a fast and efficient local search algorithm for learning finite statistical mixtures of exponential families such as Gaussian mixture models. Mixture models are traditionally learned using the expectation-maximization (EM) soft clustering technique that monotonically increases the incomplete (expec…

We show that a simple randomized sketch of the matrix multiplicative weight (MMW) update enjoys (in expectation) the same regret bounds as MMW, up to a small constant factor. Unlike MMW, where every step requires full matrix exponentiation, our steps require only a single product of the form $e^A b$, which the Lanczos …

Graphical model selection in Markov random fields is a fundamental problem in statistics and machine learning. Two particularly prominent models, the Ising model and Gaussian model, have largely developed in parallel using different (though often related) techniques, and several practical algorithms with rigorous sampl…

Motivated by applications in Game Theory, Optimization, and Generative Adversarial Networks, recent work of Daskalakis et al \cite{DISZ17} and follow-up work of Liang and Stokes \cite{LiangS18} have established that a variant of the widely used Gradient Descent/Ascent procedure, called "Optimistic Gradient Descent/Asce…

A new method for robust training under label noise using weighted gradient descent.

We tackle the issue of classifier combinations when observations have multiple views. Our method jointly learns view-specific weighted majority vote classifiers (i.e. for each view) over a set of base voters, and a second weighted majority vote classifier over the set of these view-specific weighted majority vote class…

Paper reformulates UOT as non-negative penalized linear regression for efficient algorithms.

Bio-inspired neural networks use predictive coding for efficient weight updates.

We address the challenge of designing optimal adversarial noise algorithms for settings where a learner has access to multiple classifiers. We demonstrate how this problem can be framed as finding strategies at equilibrium in a two-player, zero-sum game between a learner and an adversary. In doing so, we illustrate the…

In distributed learning, the goal is to perform a learning task over data distributed across multiple nodes with minimal (expensive) communication. Prior work (Daume III et al., 2012) proposes a general model that bounds the communication required for learning classifiers while allowing for $\eps$ training error on lin…

Study reduces NAS search cost by generating multiple complex architectures in one shot.

The (stochastic) gradient descent and the multiplicative update method are probably the most popular algorithms in machine learning. We introduce and study a new regularization which provides a unification of the additive and multiplicative updates. This regularization is derived from an hyperbolic analogue of the entr…

In this letter, we generalize the convolutional NMF by taking the $β$-divergence as the contrast function and present the correct multiplicative updates for its factors in closed form. The new updates unify the $β$-NMF and the convolutional NMF. We state why almost all of the existing updates are inexact and approximat…

In recent years, deep neural networks have found success in replicating human-level cognitive skills, yet they suffer from several major obstacles. One significant limitation is the inability to learn new tasks without forgetting previously learned tasks, a shortcoming known as catastrophic forgetting. In this research…

New scalable algorithm for non-negative linear regression with entropy-regularized OT loss.

This paper analyzes implicit bias in Deep Linear Discriminant Analysis.

Paper proposes a new activation function to reduce overfitting and large weight update issues.

This paper optimizes deep learning training by efficiently sharding weight updates across replicas.

Optimization algorithms with momentum, e.g., (ADAM), have been widely used for building deep learning models due to the faster convergence rates compared with stochastic gradient descent (SGD). Momentum helps accelerate SGD in the relevant directions in parameter updating, which can minify the oscillations of parameter…

Inverse classification uses an induced classifier as a queryable oracle to guide test instances towards a preferred posterior class label. The result produced from the process is a set of instance-specific feature perturbations, or recommendations, that optimally improve the probability of the class label. In this work…

In this paper, we extend the $β$-CNMF to two dimensions and derive exact multiplicative updates for its factors. The new updates generalize and correct the nonnegative matrix factor deconvolution previously proposed by Schmidt and Mørup. We show by simulation that the updates lead to a monotonically decreasing $β$-dive…

New insights into neural network feature learning through multi-step gradient descent.

Log-Normal Multiplicative Dynamics improves low-precision training of neural networks.

MetaGrad adapts multiple learning rates for faster online optimization.

EGAB algorithms improve online portfolio selection.

Fewer data weight updates lead to faster convergence in machine learning models.

This work analyzes how users and services adapt to reduce risk, leading to specialization.

Natural gradient learning improves synaptic plasticity in spiking neurons.

Spectral Adaptive Conformal Prediction for Structured Non-Exchangeable Data

Efficiently optimizes boolean functions using multilinear polynomials and exponential weight updates.

PipeDream-2BW accelerates large model training by 20x with minimal memory usage.

Develops theory of weightings for Lie groupoids and algebroids.

Estimates RL data for dynamic treatment effects using GMM.