Study shows E2E training fails for over-parameterized models.
problem When does E2E training fail for complex Deep Network architectures?
method Blend gradient between independent training and E2E training.
result Optimum can lie between ensemble and E2E, challenging traditional approaches.
Improved multilingual speech recognition with low latency for nine Indic languages.
problem Imbalance in training data across languages and low latency in interactive applications.
method Conditioning on a language vector and training language-specific adapter layers.
result Lower word error rate than monolingual E2E models and conventional systems.
This paper proposes an alternative to E2E training for deep networks, reducing memory footprint.
problem High GPUs memory footprint in end-to-end training of deep networks.
method Locally supervised learning with information propagation loss to avoid information collapse.
result The proposed method achieves competitive performance with less than 40% memory footprint compared to E2E training.
Improves E2E ASR performance on numeric sequences with additional training data and denormalization.
problem Challenges in recognizing numeric sequences out-of-vocabulary in ASR systems.
method Uses text-to-speech for additional numeric training data and a small-footprint neural network for denormalization.
result Reduction of WER by up to a factor of 8 in the longest numeric sequences.
CAT toolkit combines hybrid and E2E approaches for efficient speech recognition.
problem Improving speech recognition efficiency and latency.
method CTC-CRF based framework with contextualized soft forgetting.
result CAT achieves state-of-the-art results with simpler training and streaming ASR.
Proposes a method to cluster tasks for constructive cooperative multi-tasking.
problem Destructive cooperation in cooperative multi-tasking.
method Semantic clustering followed by end-to-end joint training within clusters.
result Effective mitigation of destructive cooperation and negative transfer.
E2-Train reduces training energy by 80%+ for state-of-the-art CNNs.
problem Efficient training of energy-hungry CNNs on edge devices.
method Selective layer update, stochastic mini-batch dropping, and sign prediction for low-precision backpropagation.
result Achieves >90% energy savings for training ResNet-74 on CIFAR-10.
End-to-end character-level model for text generation without delexicalization.
problem Generating text without delexicalization and tokenization.
method Character-level sequence-to-sequence model with attention mechanism, copy mechanism, and transfer learning.
result Competitive performance in text generation metrics.
Smooth maps preserve distances on specific revolution surfaces.
problem Existence of smooth maps on revolution surfaces.
method Proving existence of maps preserving distances on meridians and parallels.
result Smooth maps exist from revolution surfaces to Euclidean plane.
WaveCRN improves E2E speech enhancement with efficient CNN and SRU.
problem Efficiently modeling speech locality and sequential properties for E2E speech enhancement.
method WaveCRN uses a CNN for speech locality and SRU for temporal sequential modeling, with RFM for noise suppression.
result WaveCRN outperforms state-of-the-art approaches with reduced complexity and inference time.
We study the existence of solutions of the non-linear differential equations on the compact Riemannian manifolds (Mn,g),n≥2, Δ_p u + a(x)u^{p-1} = λf(u,x), (E2) where Δp is the p−laplacian, with 1<p<n. The equation (E2) generalizes a equation considered by Aubin, where he has considered, a compact Rieman…
Paper proposes an online speech recognition model using Transformer.
problem Challenges in deploying Transformer-based E2E ASR for online speech recognition.
method Chunk self-attention encoder (chunk-SAE) and monotonic truncated attention (MTA) based self-attention decoder (SAD).
result Achieved 23.66% CER with 320 ms latency, significant improvement over offline models.
This work improves deep learning from noisy crowdsourced labels.
problem Learning label correction and neural classifier from noisy crowdsourced data.
method Coupled Cross-Entropy Minimization (CCEM) with identifiability and regularization.
result The CCEM criterion correctly identifies annotators' confusion and neural classifier under realistic conditions.
Proposes an end-to-end deep learning framework for active investing.
problem Constructing an active investment portfolio via deep learning.
method End-to-end deep learning framework covering factor selection, combination, stock selection, and portfolio construction.
result Demonstrates effectiveness of E2E deep learning framework in active investing.
This paper improves learning complex functions with CoT supervision, reducing sample complexity.
problem Learning complex functions with multi-step reasoning.
method Develops a statistical theory linking CoT risk and end-to-end risk, using CoT information measure.
result CoT supervision can achieve significantly faster learning rates compared to standard E2E supervision.
In automatic speech recognition (ASR) what a user says depends on the particular context she is in. Typically, this context is represented as a set of word n-grams. In this work, we present a novel, all-neural, end-to-end (E2E) ASR sys- tem that utilizes such context. Our approach, which we re- fer to as Contextual Lis…
A new framework improves ASR alignment accuracy via optimal transport.
problem Peaky behavior and alignment inaccuracies in E2E ASR models.
method Differentiable alignment framework based on 1D optimal transport.
result Significant improvement in ASR alignment performance compared to CTC.
Proposes ContSup to boost local learning by supplying context between isolated modules.
problem Local learning's performance degrades with more isolated modules.
method Theoretical analysis and ContSup scheme to supply context between modules.
result Significant performance improvement with minimal overhead.
TeLeS improves ASR confidence estimation by considering temporal alignment and lexical errors.
problem Inaccurate confidence scores from E2E ASR models, especially for overconfident predictions.
method Proposes TeLeS, a novel confidence score that considers temporal alignment and lexical errors, and uses shrinkage loss to handle data imbalance.
result TeLeS generalizes well across different languages and ASR models, leading to significant WER reduction.
DiSK improves DP optimizers by simplifying Kalman filtering for better performance.
problem Performance drop of DP optimizers in large-scale training due to noise injection.
method DiSK uses Kalman filtering to denoise privatized gradients and refine gradient estimations.
result DiSK achieves significant performance improvements over standard DP optimizers in large-scale training.
Survey of graph learning methods for combinatorial optimization problems.
problem Efficient and effective analysis of graphs for combinatorial optimization problems.
method Two-stage framework: Graph representation learning followed by machine learning.
result Recent studies have shown promise in using machine learning to solve graph-based combinatorial optimization problems.
Establishes a rank inequality between knot Floer homologies of freely 2-periodic knots and their quotients.
problem Knot Floer homology of freely 2-periodic knots and their quotients
method Large's generalization of Seidel-Smith's localization spectral sequence
result Rank inequality between knot Floer homologies
We know that any element A of the group SO(3) can be represented as A = A1 A2 A1', where A1, A1' are elements of SO1(2)={A is an element of SO(3) | Ae1=e1}, and SO2(2)={A is an element of SO(3) | Ae2=e2} . This fact is known as Euler's angle. When this situation, a matrix A is called the generator. In the present paper…
Proposes LC-ST-FCN for better ride-sourcing demand forecasting.
problem Local statistical differences in ride-sourcing demand across a city.
method LC-ST-FCN framework combining 3D and 2D convolutions, locally connected layers.
result Significant improvements in demand forecasting compared to baselines.
Develops a new framework for perpetual futures on binary prediction markets.
problem Lack of effective risk management in perpetual futures on binary prediction markets.
method PIRAP framework with six components: index estimator, margin sizing, leverage, funding rule, halt protocol, and eligibility framework.
result Mixed results from empirical evaluation, with some pre-registered floors passing and others failing.
Taylorized training improves neural network training at finite width.
problem Understanding and improving neural network training at finite width.
method Training the k-th order Taylor expansion of the neural network at initialization.
result Taylorized training agrees with full neural network training better as k increases and can significantly close the performance gap.
Self-training outperforms pre-training on COCO object detection and segmentation datasets.
problem The effectiveness of pre-training in improving object detection and segmentation models is limited.
method Investigated self-training as an alternative method to utilize additional data.
result Self-training consistently improves model performance across various dataset sizes and data augmentation levels.
Un-trained neural networks outperform trained methods in MRI reconstruction.
problem Accelerated MRI reconstruction with minimal training data.
method Variation of Deep Decoder without training data.
result Un-trained approach significantly outperforms other methods in reconstruction accuracy.
Meta-learning performance depends on train-validation split type.
problem Understanding the importance of train-validation split in meta-learning.
method Theoretical and experimental study comparing train-val and train-train methods.
result Train-train method can achieve strictly better excess loss in realizable cases.
New method reveals how training data influence diffusion model outputs.
problem Difficulty in assessing training data impact on diffusion model outputs.
method Use of ensembles trained on carefully engineered splits of training data to identify influential training examples.
result Demonstrated the viability of ensembles as generative models and validity of assessing influence.
Paper shows adversarial training can be fooled by new type of noise.
problem Adversarial training can be fooled by new types of noise.
method Designing ADVIN, a new type of inducing noise.
result ADVIN can degrade adversarial training robustness by 99.9%.
New MIP methods improve training of integer-valued neural networks.
problem Training integer-valued neural networks with limited data and resources.
method Formulated new MIP models to optimize training efficiency and handle more data.
result Significantly outperforms previous state-of-the-art methods in accuracy, training time, and data usage.
Free adversarial training reduces the generalization gap compared to vanilla method.
problem Improving generalization in adversarial training.
method Analysis of algorithmic stability in free adversarial training.
result Free adversarial training shows a lower generalization gap.
ADASS selects adaptive subsets for SGD training acceleration.
problem Fixed sample size in SGD limits training efficiency.
method ADASS selects adaptive subsets based on Lipschitz constants.
result ADASS achieves comparable accuracy with full training set.
Solve-training trains neural nets to map physical solutions efficiently.
problem Representing complex physical solutions with neural networks.
method Variational training using loss functions from physical models.
result Effective neural network representation of solution maps without expensive labels.
Making neural networks robust against adversarial inputs has resulted in an arms race between new defenses and attacks. The most promising defenses, adversarially robust training and verifiably robust training, have limitations that restrict their practical applications. The adversarially robust training only makes the…
learn2mix trains neural nets faster by adjusting class proportions dynamically.
problem Training neural nets efficiently with limited resources and imbalanced classes.
method Adaptive class proportion adjustment during training.
result Neural nets trained with learn2mix converge faster than static methods.
Loss-guided training accelerates node embedding methods on graphs.
problem Training efficiency in graph learning methods with implicit positive examples.
method Dynamic adjustment of training distribution based on loss values.
result Significant acceleration in training and computation over static methods.
Paper explores fast adversarial training to improve robustness with less computation.
problem Efficiently defending against adversarial examples.
method Integrates simple self-attacks for faster training, focusing on overfitting recovery.
result Shows superior robust accuracy with reduced training time compared to strong adversarial training.
Free adversarial training improves robustness without generating adversarial examples.
problem Training robust models against adversarial attacks is costly and impractical for large-scale datasets.
method Recycles gradient information from parameter updates to generate adversarial examples.
result Free adversarial training achieves comparable robustness to PGD training at negligible cost.
Detects backdoors in trained models without poisoned training data.
problem Detecting backdoors in DNNs trained without access to the poisoned training set.
method Proposes a novel detector using the maximum achievable misclassification fraction (MAMF) statistic.
result Detects backdoors and infers source and target classes.
Crowdsourced training of large neural networks with decentralized Mixture-of-Experts.
problem Expensive training of large neural networks limits research contributions.
method Learning@home: decentralized Mixture-of-Experts for large, poorly connected participants.
result Performance and reliability of Learning@home surpass conventional distributed training.
Pre-training is crucial for learning deep neural networks. Most of existing pre-training methods train simple models (e.g., restricted Boltzmann machines) and then stack them layer by layer to form the deep structure. This layer-wise pre-training has found strong theoretical foundation and broad empirical support. Howe…
New method reconstructs significant parts of training data from neural networks.
problem Understanding and reconstructing training data from neural networks.
method Proposes a novel reconstruction scheme based on recent theoretical results about neural network training.
result Shows that a significant fraction of training data can be reconstructed from neural network parameters.
The paper studies the asymptotic behavior of adversarial training under ℓ∞-perturbation.
problem Theoretical guarantees for sparsity-recovery in adversarial training.
method Investigation of the asymptotic distribution of the adversarial training estimator in generalized linear models.
result The asymptotic distribution of the adversarial training estimator under ℓ∞-perturbation could have a positive probability mass at 0 when the true parameter is 0. This paper introduces 'General Cyclical Training' for neural networks.
problem Improving training efficiency and performance of neural networks.
method Cyclical training phases with varying hyperparameters, batch sizes, loss functions, and data augmentation.
result Cyclical weight decay, softmax temperature, and gradient clipping enhance model accuracy.
Speeds up training and inference by pruning entire channels before training.
problem Training and inference speed in deep neural networks.
method Structured pruning applied before training, focusing on removing entire channels and hidden units.
result 2x speedup in training and 3x speedup in inference.
The paper predicts loss scaling across different datasets and compute scales.
problem Predicting loss scaling across different datasets and compute scales.
method Derive shifted power law relationships between train and test losses.
result Shifted power law relationships hold for various datasets and tasks, improving prediction accuracy.