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.
Paper proposes a new activation function to reduce overfitting and large weight update issues.
In importance sampling (IS)-based reinforcement learning algorithms such as Proximal Policy Optimization (PPO), IS weights are typically clipped to avoid large variance in learning. However, policy update from clipped statistics induces large bias in tasks with high action dimensions, and bias from clipping makes it di…
This paper optimizes deep learning training by efficiently sharding weight updates across replicas.
Pion optimizes LLMs by preserving weight matrix singular values.
Paper proposes efficient weight updates for edge nodes with minimal communication.
Improves inference-time alignment for diffusion models without updating weights.
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…
Evolution Strategies (ES) emerged as a scalable alternative to popular Reinforcement Learning (RL) techniques, providing an almost perfect speedup when distributed across hundreds of CPU cores thanks to a reduced communication overhead. Despite providing large improvements in wall-clock time, ES is data inefficient whe…
Sparse random networks reduce communication in federated learning.
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…
In-Place TTT enhances LLMs with dynamic parameter updates at inference time.
PLUMAGE improves large model training efficiency and stability.
Study on learning rates in neural networks of varying depth.
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…
RSO uses random weight perturbations to train deep networks without gradients.
Paper proves multiplicative weight updates can train neural networks without learning rate tuning.
We describe -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…
Benefitting from large-scale training datasets and the complex training network, Convolutional Neural Networks (CNNs) are widely applied in various fields with high accuracy. However, the training process of CNNs is very time-consuming, where large amounts of training samples and iterative operations are required to ob…
PipeDream-2BW accelerates large model training by 20x with minimal memory usage.
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 …
Bio-inspired neural networks use predictive coding for efficient weight updates.
PAC-Net prunes deep models for better transfer learning.
We show how to convert ICL in linearized transformers into model weights.
In this paper, we propose a method for training neural networks when we have a large set of data with weak labels and a small amount of data with true labels. In our proposed model, we train two neural networks: a target network, the learner and a confidence network, the meta-learner. The target network is optimized to…
We consider the task of one-shot learning of visual categories. In this paper we explore a Bayesian procedure for updating a pretrained convnet to classify a novel image category for which data is limited. We decompose this convnet into a fixed feature extractor and softmax classifier. We assume that the target weights…
It is inevitable to train large deep learning models on a large-scale cluster equipped with accelerators system. Deep gradient compression would highly increase the bandwidth utilization and speed up the training process but hard to implement on ring structure. In this paper, we find that redundant gradient and gradien…
Optimal client sampling reduces communication in federated learning.
Method reweights instances and classes to improve robustness in noisy data.
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…
Fewer data weight updates lead to faster convergence in machine learning models.
SnAp approximates RTRL for online training of sparse recurrent networks.
Flora uses random projections to achieve high-rank updates with low memory usage.
Neural networks are easier to optimise when they have many more weights than are required for modelling the mapping from inputs to outputs. This suggests a two-stage learning procedure that first learns a large net and then prunes away connections or hidden units. But standard training does not necessarily encourage ne…
New algorithm for online optimization over symmetric cones, unifying previous methods.
Spectral Adaptive Conformal Prediction for Structured Non-Exchangeable Data
Training deep neural networks on large-scale datasets requires significant hardware resources whose costs (even on cloud platforms) put them out of reach of smaller organizations, groups, and individuals. Backpropagation, the workhorse for training these networks, is an inherently sequential process that is difficult t…
Long Short-Term Memory networks trained with gradient descent and back-propagation have received great success in various applications. However, point estimation of the weights of the networks is prone to over-fitting problems and lacks important uncertainty information associated with the estimation. However, exact Ba…
Efficiently optimizes boolean functions using multilinear polynomials and exponential weight updates.
Introduces Causal Energy Minimization to understand Transformer layers.
This paper studies recursive ensembles driven by Fibonacci updates, improving learning dynamics.
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…
This paper analyzes implicit bias in Deep Linear Discriminant Analysis.
Importance sampling (IS) is a common reweighting strategy for off-policy prediction in reinforcement learning. While it is consistent and unbiased, it can result in high variance updates to the weights for the value function. In this work, we explore a resampling strategy as an alternative to reweighting. We propose Im…
New analysis shows how cross-entropy training shapes attention in transformers.
Efficiently updates beliefs with virtual observations.
We introduce a new sub-linear space sketch---the Weight-Median Sketch---for learning compressed linear classifiers over data streams while supporting the efficient recovery of large-magnitude weights in the model. This enables memory-limited execution of several statistical analyses over streams, including online featu…
RIFLE improves deep transfer learning by reinitializing fully-connected layers.