Paper proposes efficient weight updates for edge nodes with minimal communication.
problem Inefficient and resource-intensive full weight updates for edge nodes.
method Deep partial updating, selecting a subset of weights to update.
result Achieves similar performance with fewer weight updates.
Paper compresses neural network weight-updates for image artifacts removal.
problem Efficiently compressing neural network weight-updates for image artifacts removal.
method Fine-tuning a pre-trained artifact removal network on target data with a compression objective that encourages sparse and quantized weight-updates.
result Achieves reconstruction quality comparable to traditional codecs at comparable bitrates.
Deep networks trained with Hebbian updates perform similarly to back-propagation on image datasets.
problem Training deep networks with realistic asymmetric connections and updates.
method Use Hebbian updates with separate feedforward and feedback weights, and local rule for updates.
result Similar performance to back-propagation achieved with Hebbian updates on challenging image datasets.
A new technique updates weights multiple times for online learning, reducing mistakes to near zero.
problem Online learning with partial data and unknown future data points.
method Iterative weight updating for the same instance.
result Reduced mistake rate to near zero for various datasets and algorithms.
RSO uses random weight perturbations to train deep networks without gradients.
problem Training deep neural networks efficiently and without gradient information.
method RSO is a gradient-free Markov Chain Monte Carlo approach that updates weights based on mini-batch loss reduction.
result RSO achieves high accuracy (99.1% on MNIST) with significantly fewer updates than traditional methods.
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…
Paper proves multiplicative weight updates can train neural networks without learning rate tuning.
problem Vanishing and exploding gradients in gradient descent for compositional functions.
method Proves descent lemma for compositional functions using multiplicative weight updates and derives Madam optimizer.
result Madam optimizer trains state-of-the-art neural networks without learning rate tuning.
Bio-inspired neural networks use predictive coding for efficient weight updates.
problem Training artificial neural networks efficiently and biologically plausibly.
method Predictive Coding (PC) updates weights locally using only local information.
result PC provides theoretical advantages like automatic gradient scaling.
DEAM optimizes momentum weights dynamically to improve deep learning model training.
problem Errors in momentum weights propagate errors in optimization algorithms like ADAM.
method DEAM computes adaptive momentum weights based on discriminative angles, reducing hyperparameters and introducing a backtrack term.
result DEAM achieves faster convergence rates in both convex and non-convex deep learning model training.
Paper proposes a new activation function to reduce overfitting and large weight update issues.
problem Overfitting and large weight update problems in neural networks.
method Introduces a new activation function called Thresholded Exponential Rectified Linear Units (TERELU).
result TERELU shows better performance in reducing overfitting and large weight update issues compared to other activation functions.
This paper optimizes deep learning training by efficiently sharding weight updates across replicas.
problem Redundant weight update computation on all replicas in data-parallel training.
method Automatic sharding of weight updates using static analysis and transformations on the training graph.
result Substantial speedups achieved on large-scale models using Cloud TPUs.
Fewer data weight updates lead to faster convergence in machine learning models.
problem Improving robustness of machine learning models through data mixing.
method Analyzing convergence behavior of data mixing with a finite number of inner steps.
result The optimal number of inner steps scales with the budget and type of gradients used.
New algorithm for online optimization over symmetric cones, unifying previous methods.
problem Online convex optimization over symmetric cones.
method Symmetric-Cone Multiplicative Weights Update (SCMWU) algorithm.
result SCMWU is a no-regret algorithm.
Spectral Adaptive Conformal Prediction for Structured Non-Exchangeable Data
problem Improving prediction intervals for non-exchangeable time-indexed datasets
method Spectral adaptive conformal prediction
result Improves on fixed spectral weighting while monitoring uncertainty changes
Efficiently optimizes boolean functions using multilinear polynomials and exponential weight updates.
problem Optimizing boolean functions over the boolean hypercube with high computational cost.
method Proposes a computationally efficient algorithm using multilinear polynomials and exponential weight updates.
result Improves computational time up to several orders of magnitude compared to state-of-the-art algorithms.
Sparse random networks reduce communication in federated learning.
problem Large communication cost in federated learning.
method Freeze random weights, train stochastic binary mask to sparsify.
result Improves accuracy, reduces communication, speeds convergence.
This paper studies recursive ensembles driven by Fibonacci updates, improving learning dynamics.
problem Improving learning dynamics in recursive ensemble learning.
method Develops second-order recursive architectures with Fibonacci-type update flows.
result Establishes global convergence conditions and generalization bounds for recursive ensembles.
This paper considers the actor-critic contextual bandit for the mobile health (mHealth) intervention. The state-of-the-art decision-making methods in mHealth generally assume that the noise in the dynamic system follows the Gaussian distribution. Those methods use the least-square-based algorithm to estimate the expect…
Improves inference-time alignment for diffusion models without updating weights.
problem Aligning diffusion models without updating weights for high-reward outputs.
method Trust-Region Iterative Twisted Sequential Monte Carlo (TRI-TSMC) for variance reduction and efficiency.
result Improves primary alignment objectives on text generation tasks.
Efficiently updates beliefs with virtual observations.
problem Incremental belief updates in Bayesian models.
method Constructs weighted virtual observations to match posterior.
result Reconstructed posterior matches original posterior closely.
A RL approach dynamically assigns and updates weights of ensemble models for better time series forecasting.
problem Static weight assignment for ensemble models fails to capture dynamic data changes.
method Reinforcement Learning (RL) to dynamically update weights of each model at different time instants.
result Dynamic weighted approach using RL learns weights better than static methods.
We consider a setting where an agent's uncertainty is represented by a set of probability measures, rather than a single measure. Measure-bymeasure updating of such a set of measures upon acquiring new information is well-known to suffer from problems; agents are not always able to learn appropriately. To deal with the…
A new accelerated method with simpler momentum update rules.
problem Optimizing parameters in machine learning models.
method Proposes a novel accelerated stochastic gradient method with simpler momentum update rules.
result The method outperforms Sgdm and Adam in practical problems.
Bayesian neural networks learn weights with closed-form updates.
problem Efficiently learning Bayesian neural networks with closed-form updates.
method Closed-form Bayesian inference for online learning of Gaussian-weighted BNNs.
result Closed-form expressions for sequential/online training of BNNs.
We present a confidence-based single-layer feed-forward learning algorithm SPIRAL (Spike Regularized Adaptive Learning) relying on an encoding of activation spikes. We adaptively update a weight vector relying on confidence estimates and activation offsets relative to previous activity. We regularize updates proportion…
GFM models neural network training as a dynamical system to forecast final weights.
problem Computational intensity and inefficiency in training deep neural networks.
method Gradient Flow Matching (GFM) treats training as a dynamical system with learned vector fields.
result GFM achieves forecasting accuracy competitive with Transformer-based models and significantly outperforms classical baselines.
A new resampling strategy, Importance Resampling, improves sample efficiency and reduces variance in off-policy prediction.
problem High variance updates in importance sampling for off-policy prediction.
method Importance Resampling (IR) resamples experience from a replay buffer and applies standard on-policy updates, avoiding importance sampling ratios.
result Importance Resampling (IR) shows improved sample efficiency and lower variance updates compared to other methods.
A novel Bayesian computation method using importance weighting improves numerical stability and performance.
problem Bayesian computation stability and performance issues.
method Nonparametric approach via feature means, importance weighting, and kernel Bayes' rule.
result Importance weighted kernel Bayes' rule yields superior numerical stability and performance.
Pion optimizes LLMs by preserving weight matrix singular values.
problem Training large language models (LLMs) with standard optimizers leads to unstable weight matrices.
method Pion uses orthogonal transformations to update weight matrices, preserving their singular values.
result Pion offers a stable alternative to standard optimizers for LLM pretraining and finetuning.
EP learns like BPTT but with local weight updates.
problem Existing EP lacks a local time learning rule.
method C-EP updates weights simultaneously with neuron dynamics.
result C-EP follows BPTT gradients and performs well.
New method reduces bias in high-dimensional action spaces for efficient reinforcement learning.
problem Large bias and difficulty in reusing old samples in high-dimensional action spaces.
method Dimension-wise IS weight clipping to control bias and adaptively manage IS weights.
result Proposed method outperforms PPO and other RL algorithms in various tasks.
Adaptive learning of sample weights for better model performance.
problem Overfitting to biased training data with corrupted labels or class imbalance.
method Adaptive learning of an explicit weighting function using a meta-weight-net.
result Improves model accuracy in class imbalance and noisy label cases.
New algorithm uses PSO to optimize DNN training parameters in distributed systems.
problem Reducing synchronization frequency in DNN training leads to poor convergence.
method Integrates PSO into distributed training to automatically compute new parameters.
result Proposed algorithm outperforms synchronous methods in distributed DNN training.
Study on learning rates in neural networks of varying depth.
problem Dependence of maximal update learning rate on network depth.
method Analysis of random fully connected ReLU networks with mean-field weight initialization.
result Maximal update learning rate scales like L−3/2 with network depth. Gradient-based methods introduce noise that penalizes models sensitive to weight perturbations.
problem Noise in gradient-based optimization methods.
method Analysis of Gradient Descent (GD) and Stochastic Gradient Descent (SGD) updating all parameters simultaneously.
result Noise introduced by simultaneous parameter updates penalizes models sensitive to weight perturbations.
Enhances linear regression with Kalman filter for loss minimization.
problem Minimizing loss in linear regression models.
method Integrates Kalman filter and SGD for optimal weight updates.
result Develops optimal linear regression equation with minimum area under curve.
TSC improves causal effect estimation in panel data.
problem Estimating causal effects in panel data with a single treated unit.
method Targeted synthetic control method that refines initial weights through a one-dimensional targeted update.
result TSC consistently improves estimation accuracy over state-of-the-art SCM baselines.
Non-negative matrix factorization is a popular tool for decomposing data into feature and weight matrices under non-negativity constraints. It enjoys practical success but is poorly understood theoretically. This paper proposes an algorithm that alternates between decoding the weights and updating the features, and sho…
In this paper we revisit the weighted likelihood bootstrap, a method that generates samples from an approximate Bayesian posterior of a parametric model. We show that the same method can be derived, without approximation, under a Bayesian nonparametric model with the parameter of interest defined as minimising an expec…
In-Place TTT enhances LLMs with dynamic parameter updates at inference time.
problem Static training limits LLMs from adapting to new information.
method In-Place TTT updates a subset of model parameters (fast weights) at inference time.
result In-Place TTT enables 4B-parameter models to outperform on tasks with up to 128k contexts.
Efficient algorithm removes redundant nodes and obsolete samples in machine learning.
problem Pruning redundant nodes and removing obsolete training samples in machine learning.
method Deduced decremented learning algorithms from incremental learning algorithms, using inverse Cholesterol factor and unitary transformation.
result Proposed decremented learning algorithms efficiently prune redundant nodes and remove obsolete training samples.
Background: Deep learning models are typically trained using stochastic gradient descent or one of its variants. These methods update the weights using their gradient, estimated from a small fraction of the training data. It has been observed that when using large batch sizes there is a persistent degradation in genera…
We introduce a minorization-maximization approach to optimizing common measures of discovery significance in high energy physics. The approach alternates between solving a weighted binary classification problem and updating class weights in a simple, closed-form manner. Moreover, an argument based on convex duality sho…
To recover a sparse signal from an underdetermined system, we often solve a constrained L1-norm minimization problem. In many cases, the signal sparsity and the recovery performance can be further improved by replacing the L1 norm with a "weighted" L1 norm. Without any prior information about nonzero elements of the si…
Study reveals dynamics of neural networks with normalization, weight decay, and SGD.
problem Understanding the equilibrium condition in Spherical Motion Dynamics (SMD).
method Investigates SMD by exploring the cause of equilibrium condition, introducing assumptions, proposing angular update, and verifying theoretical results.
result Proves weight norm and angular update can converge at linear rate under given assumptions.
New algorithm provably converges to second-order stationary points in NMF.
problem Understanding convergence to local minima in NMF.
method Multiplicative weight update dynamics, concurrent updates, and simplex reduction.
result Provable convergence to second-order stationary points.
New sketches for weighted ℓp sampling without replacement improve accuracy and efficiency.
problem Efficiently sampling weighted data with high accuracy and minimal redundancy.
method Design of novel composable sketches for WOR ℓp sampling, based on CountSketch. result First to provide WOR sampling for p>1 and signed updates. Traditionally, deep learning algorithms update the network weights whereas the network architecture is chosen manually, using a process of trial and error. In this work, we propose two novel approaches that automatically update the network structure while also learning its weights. The novelty of our approach lies in o…