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 method to measure model sensitivity using final model only.
New method improves black-box attacks using pre-trained models.
New view: Deep GCNs learn to anti-oversmooth during training.
ES improves training efficiency by dynamically selecting data samples.
We introduce a training method for both better word representation and performance, which we call GROVER (Gradual Rumination On the Vector with maskERs). The method is to gradually and iteratively add random noises to word embeddings while training a model. GROVER first starts from conventional training process, and th…
Convolutional neural networks have achieved astonishing results in different application areas. Various methods that allow us to use these models on mobile and embedded devices have been proposed. Especially binary neural networks are a promising approach for devices with low computational power. However, training accu…
In this contribution, we augment the metric learning setting by introducing a parametric pseudo-distance, trained jointly with the encoder. Several interpretations are thus drawn for the learned distance-like model's output. We first show it approximates a likelihood ratio which can be used for hypothesis tests, and th…
EigenNoise provides a competitive word vector initialization scheme without pre-training data.
Deep Reinforcement Learning (RL) is proven powerful for decision making in simulated environments. However, training deep RL model is challenging in real world applications such as production-scale health-care or recommender systems because of the expensiveness of interaction and limitation of budget at deployment. One…
Two things seem to be indisputable in the contemporary deep learning discourse: 1. The categorical cross-entropy loss after softmax activation is the method of choice for classification. 2. Training a CNN classifier from scratch on small datasets does not work well. In contrast to this, we show that the cosine loss fun…
SGD updates align with a low-rank subspace but do not lead to further loss reduction.
Efficiently trains GCNs with reduced time and memory usage.
This paper considers object detection and 3D estimation using an FMCW radar. The state-of-the-art deep learning framework is employed instead of using traditional signal processing. In preparing the radar training data, the ground truth of an object orientation in 3D space is provided by conducting image analysis, of w…
EntProp increases entropy of clean samples to generate out-of-distribution data for better DNN performance.
Extract synthetic data from pretrained models for tasks without training data.
MeLa learns task relations by inferring global labels for robust FSL.
The paper analyzes the training dynamics of a transformer for next-token prediction.
The abstract proves the existence of universal lottery tickets without needing further training.
Paper optimizes change-point detection using learned distributions from training sequences.
Carbon capture and storage (CCS) can aid decarbonization of the atmosphere to limit further global temperature increases. A framework utilizing unsupervised learning is used to generate a range of subsurface geologic volumes to investigate potential sites for long-term storage of carbon dioxide. Generative adversarial …
Modern machine learning models are typically trained using Stochastic Gradient Descent (SGD) on massively parallel computing resources such as GPUs. Increasing mini-batch size is a simple and direct way to utilize the parallel computing capacity. For small batch an increase in batch size results in the proportional red…
We have recently shown that deep Long Short-Term Memory (LSTM) recurrent neural networks (RNNs) outperform feed forward deep neural networks (DNNs) as acoustic models for speech recognition. More recently, we have shown that the performance of sequence trained context dependent (CD) hidden Markov model (HMM) acoustic m…
New framework for DNN training guarantees convergence to global minimum.
Whether neural networks can learn abstract reasoning or whether they merely rely on superficial statistics is a topic of recent debate. Here, we propose a dataset and challenge designed to probe abstract reasoning, inspired by a well-known human IQ test. To succeed at this challenge, models must cope with various gener…
We explore training an automatic modality tagger. Modality is the attitude that a speaker might have toward an event or state. One of the main hurdles for training a linguistic tagger is gathering training data. This is particularly problematic for training a tagger for modality because modality triggers are sparse for…
Framework generates fair synthetic data to avoid biases.
In our previous work we have shown that resistive cross point devices, so called Resistive Processing Unit (RPU) devices, can provide significant power and speed benefits when training deep fully connected networks as well as convolutional neural networks. In this work, we further extend the RPU concept for training re…
Simpler autoencoder with regularization outperforms complex alternatives.
We propose two approaches of locally adaptive activation functions namely, layer-wise and neuron-wise locally adaptive activation functions, which improve the performance of deep and physics-informed neural networks. The local adaptation of activation function is achieved by introducing a scalable parameter in each lay…
We present the remote stochastic gradient (RSG) method, which computes the gradients at configurable remote observation points, in order to improve the convergence rate and suppress gradient noise at the same time for different curvatures. RSG is further combined with adaptive methods to construct ARSG for acceleration…
Hessian-free training has become a popular parallel second or- der optimization technique for Deep Neural Network training. This study aims at speeding up Hessian-free training, both by means of decreasing the amount of data used for training, as well as through reduction of the number of Krylov subspace solver iterati…
A new scaling law predicts optimal batch size for training models.
Paper improves deep learning for instance-level classification from label proportions.
This paper explores the use of adversarial examples in training speech recognition systems to increase robustness of deep neural network acoustic models. During training, the fast gradient sign method is used to generate adversarial examples augmenting the original training data. Different from conventional data augmen…
Dynamic pruning during training reduces deep network complexity without significant accuracy loss.
Dropout, a simple and effective way to train deep neural networks, has led to a number of impressive empirical successes and spawned many recent theoretical investigations. However, the gap between dropout's training and inference phases, introduced due to tractability considerations, has largely remained under-appreci…
Proposes EM-HRNN model for better hierarchical language representation.
Background: It is still an open research area to theoretically understand why Deep Neural Networks (DNNs)---equipped with many more parameters than training data and trained by (stochastic) gradient-based methods---often achieve remarkably low generalization error. Contribution: We study DNN training by Fourier analysi…
A key learning scenario in large-scale applications is that of federated learning, where a centralized model is trained based on data originating from a large number of clients. We argue that, with the existing training and inference, federated models can be biased towards different clients. Instead, we propose a new f…
We propose a max-pooling based loss function for training Long Short-Term Memory (LSTM) networks for small-footprint keyword spotting (KWS), with low CPU, memory, and latency requirements. The max-pooling loss training can be further guided by initializing with a cross-entropy loss trained network. A posterior smoothin…
Deep learning algorithms have recently produced state-of-the-art accuracy in many classification tasks, but this success is typically dependent on access to many annotated training examples. For domains without such data, an attractive alternative is to train models with light, or distant supervision. In this paper, we…
Models applied on real time response task, like click-through rate (CTR) prediction model, require high accuracy and rigorous response time. Therefore, top-performing deep models of high depth and complexity are not well suited for these applications with the limitations on the inference time. In order to further impro…
TxSim models DNN training on resistive crossbars, improving accuracy and feasibility.
Language is increasingly being used to define rich visual recognition problems with supporting image collections sourced from the web. Structured prediction models are used in these tasks to take advantage of correlations between co-occurring labels and visual input but risk inadvertently encoding social biases found i…
We present a novel approach to leverage large unlabeled datasets by pre-training state-of-the-art deep neural networks on randomly-labeled datasets. Specifically, we train the neural networks to memorize arbitrary labels for all the samples in a dataset and use these pre-trained networks as a starting point for regular…
While noise is commonly considered a nuisance in computing systems, a number of studies in neuroscience have shown several benefits of noise in the nervous system from enabling the brain to carry out computations such as probabilistic inference as well as carrying additional information about the stimuli. Similarly, no…
Progressive Neural Network Learning is a class of algorithms that incrementally construct the network's topology and optimize its parameters based on the training data. While this approach exempts the users from the manual task of designing and validating multiple network topologies, it often requires an enormous numbe…
A new framework for offline RL improves policy flexibility and regularity.