Sparse Attentive Backtracking selectively backpropagates long-term dependencies in recurrent networks.
problem Difficulty in learning long-term dependencies in BPTT due to computational impracticality and biased gradient estimates.
method Sparse Attentive Backtracking learns an attention mechanism over past hidden states and selectively backpropagates through high-weight paths.
result Model learns long-term dependencies with fewer backpropagation steps, addressing biased gradient issues.
TFM trains Neural SDEs without backpropagation, improving clinical time series modeling.
problem Modeling irregularly sampled time series in medicine.
method Trajectory Flow Matching (TFM) using flow matching for generative modeling.
result TFM improves performance on clinical time series datasets.
Unified framework for faster neural network training with less information loss.
problem Time-consuming backpropagation and loss of unpropagated gradient information.
method Unified sparse backpropagation framework and memorized sparse backpropagation algorithm.
result Convergence in probability with certain conditions and effective information loss mitigation.
SnAp approximates RTRL for online training of sparse recurrent networks.
problem Training large sparse recurrent networks online is computationally expensive.
method Sparse n-step Approximation (SnAp) of the RTRL influence matrix.
result SnAp with n=2 remains tractable for highly sparse networks and outperforms backpropagation through time.
New method reduces memory usage in deep HRNNs by replacing gradient backpropagation with local losses.
problem Memory constraints in training deep hierarchical RNNs.
method Replace gradient backpropagation with locally computable losses in deep HRNNs.
result Memory requirements reduced by a factor exponential in hierarchy depth.
A method for learning sparse transformations through backpropagation.
problem Sparse transformations in deep learning architectures are hard to design and often represented densely during learning.
method Adaptive, sparse hyperlayer with randomly sampled connections to overcome gradient issues.
result Trained models achieve competitive performance on real data.
New ODE solvers improve training efficiency and accuracy.
problem Training Neural ODEs requires efficient and accurate gradient calculation.
method Presented algebraically reversible ODE solvers that are time and memory efficient, calculate exact gradients, and are numerically stable.
result Reversible solvers strictly improve upon previous architectures in efficiency and accuracy.
Improved BER with reduced power in time-domain digital backpropagation.
problem Improving BER performance in time-domain digital backpropagation.
method Jointly optimized and quantized chromatic dispersion filters using machine learning.
result Improved BER performance and power dissipation reductions.
Demon aligns diffusion models without retraining or backpropagation.
problem Aligning diffusion models with user preferences.
method Stochastic optimization to control noise distribution.
result Significantly improves aesthetics scores for text-to-image generation.
Gradient flossing stabilizes RNN training by controlling Lyapunov exponents.
problem Gradient instability in RNNs leading to exploding and vanishing gradients.
method Regularizing Lyapunov exponents through backpropagation using differentiable linear algebra.
result Gradient flossing improves RNN training success rate and convergence speed.
Paper proposes DAG-DB for learning discrete DAGs via backpropagation.
problem Learning Directed Acyclic Graphs (DAGs) from data.
method DAG-DB uses Discrete Backpropagation with I-MLE and Straight-Through Estimation.
result DAG-DB learns DAGs effectively using probabilistic sampling and backpropagation.
Adaptive TBPTT controls gradient bias in RNNs for faster convergence.
problem Choosing optimal truncation length in TBPTT for RNNs is difficult.
method Adaptive TBPTT converts lag selection to bias control, estimating optimal truncation length during training.
result Adaptive TBPTT improves convergence rate and computational efficiency in RNNs.
Study proposes memory-efficient backpropagation for linear layers in neural networks.
problem Significant memory usage in backpropagation through linear layers in neural networks.
method Randomized matrix multiplications to reduce memory usage with a moderate decrease in test accuracy.
result Demonstrated benefits of the proposed method on fine-tuning pre-trained models.
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.
This work shows synthetic gradients can outperform backpropagation in sample efficiency.
problem The efficiency of backpropagation in training neural networks.
method Unified vectorized feedback framework for loss-based and reward-based learning, introducing synthetic gradients.
result Synthetic gradients can achieve lower gradient-estimation mean squared error than backpropagation under certain conditions.
A new memory strategy extends BPTT's learning window without longer traces.
problem Learning distant correlations in reinforcement learning requires efficient memory and learning strategies.
method Proposes a simple, effective memory strategy for extending BPTT's learning window.
result Extends BPTT's learning window without longer traces, improving efficiency.
Train deep neural networks one layer at a time for faster training and flexibility.
problem Training deep neural networks efficiently and with diverse layers.
method Train layers sequentially, mapping input data forward through each layer.
result Achieved state-of-the-art accuracy on MNIST dataset for convolutional neural networks.
This paper improves RNNs' ability to handle long-term dependencies using an auxiliary loss.
problem Capturing long-term dependencies in RNNs is challenging.
method Adds an unsupervised auxiliary loss to improve long-term dependency capture.
result Improves performance and resource efficiency over competitive baselines.
Paper proposes a neural network method for fast, interpretable AR model estimation.
problem Computational inefficiency and convergence issues in conventional AR model estimation.
method Embeds autoregressive structure into a feedforward neural network for coefficient estimation via backpropagation.
result Neural network method consistently recovers AR model coefficients, converging in all cases and providing reliable estimates.
ARSM estimator improves gradient backpropagation for categorical variables.
problem Improving gradient backpropagation through categorical variables.
method ARSM combines variable augmentation, REINFORCE, Rao-Blackwellization, and variable swapping.
result ARSM outperforms existing estimators and provides variance reduction methods.
A new method for backpropagating through categorical distributions.
problem Difficulty in backpropagating through categorical latent variables in neural networks.
method Introducing Gumbel-Softmax distribution for differentiable sampling.
result Gumbel-Softmax estimator outperforms existing methods on tasks with categorical latent variables.
We introduce the "NoBackTrack" algorithm to train the parameters of dynamical systems such as recurrent neural networks. This algorithm works in an online, memoryless setting, thus requiring no backpropagation through time, and is scalable, avoiding the large computational and memory cost of maintaining the full gradie…
Backprop-Q extends standard backpropagation for stochastic computation graphs.
problem Applying standard backpropagation to stochastic computation graphs is challenging.
method Construct Q-functions for each stochastic node and use them to train the SCG with standard backpropagation.
result Generalized backpropagation for stochastic computation graphs is feasible and extends learning signals beyond gradients.
Belief propagation recovers backpropagation results.
problem Connection between backpropagation and belief propagation poorly understood.
method Converted backpropagation input to belief propagation input and showed results.
result Backpropagation is a special case of belief propagation.
VSML unifies meta learning concepts and enables simple backpropagation.
problem Improving and unifying meta learning concepts for neural networks.
method Unified approach using variable shared meta learning and simple weight-sharing.
result Simple backpropagation can be implemented and meta learned without gradient calculation.
Spectral backpropagation optimizes implicit likelihoods without explicit assumptions.
problem Training systems without explicit goals and likelihood functions.
method Spectral backpropagation for implicit likelihood optimization.
result Identified two novel properties of GAN generators: aberrant outputs and quasi-disentangled factors.
Sideways trains video models by overwriting activations as new frames arrive, potentially improving generalization.
problem Training deep video models synchronously slows down and requires storing activations, limiting parallelism.
method Sideways trains video models by overwriting activations as new frames arrive, breaking the precise correspondence between gradients and activations.
result Sideways training can converge and potentially generalize better than standard synchronized backpropagation.
EP matches BPTT gradients in discrete-time RNNs, improving training efficiency.
problem Training convergent RNNs efficiently with EP.
method Introduced a discrete-time version of EP with simplified equations and backward gradients.
result EP's neural and weight updates are step-by-step equal to BPTT's, with gradients computed backward.
Neural controlled DEs model irregular time series by adjusting based on observations.
problem Modeling irregularly sampled multivariate time series with memory-efficient adjoint-based backpropagation.
method Neural controlled differential equations (CDEs) that adjust based on subsequent observations.
result Achieves state-of-the-art performance on various datasets.
Backpropagation-free RL method trains layers using local signals.
problem Vanishing or exploding gradients in backpropagation-based RL.
method Local pairwise distance matching for layer-wise training without backpropagation.
result Backpropagation-free method achieves competitive performance and stability.
ZORB speeds up neural network training without sacrificing accuracy.
problem Slow and strenuous training of neural networks using gradient descent.
method Uses pseudoinverse of targets instead of gradients for backpropagation.
result ZORB converges 300 times faster than Adam on MNIST without hyperparameter tuning.
A new algorithm reduces the computational cost of RTRL while maintaining performance.
problem Large computational costs in RTRL for learning long-term dependencies.
method Optimal Kronecker-Sum Approximation (OK) of RTRL.
result OK is optimal for a class of RTRL approximations and matches TBPTT in performance.
New neural network theory mimics physics laws, making computations more plausible.
problem Neural networks lack biological plausibility in computations.
method Variational framework of the least action principle, local in space and time.
result SpatioTemporal Local Propagation (STLP) scheme is biologically plausible.
Solla discusses neural processing using statistical physics and Bayesian methods.
problem Understanding neural information processing through statistical physics.
method Bayesian inference, Gibbs description, Generalized Linear Models, dimensionality reduction.
result Connection between neural processing and statistical physics.
A new method distills datasets more efficiently and effectively.
problem Achieving competitive performance on test data with a small synthetic dataset.
method Tackles dataset distillation as a bilevel optimization problem, introduces RaT-BPTT to stabilize gradients and speed up optimization.
result Establishes new state-of-the-art performance across various benchmarks.
Mean field theory explains gradient backpropagation in deep dropout networks.
problem Understanding gradient backpropagation in deep dropout networks.
method Applied mean field theory to dropout networks, considering realistic training conditions.
result Gradient backpropagation length is limited by depth scales, not just independence assumption.
Improved signal processing for long-distance optical signals.
problem Compensating walk-off effect in long-distance optical signals.
method Sub-banded DSP architecture with deep learning for walk-off compensation.
result 2.8 dB SNR improvement over linear equalization.
FPGA-based multi-layer equalizer adapts to changing channels.
problem Real-time adaptation to time-varying channel impairments.
method Multi-layer machine learning on FPGA with on-chip gradient backpropagation training.
result Real-time adaptation to changing channel conditions achieved.
Deep learning approach to inverse optimization.
problem Determine parameters of an optimization process from observations.
method Unroll iterative optimization, use backpropagation to learn parameters.
result Learn coefficients for cost vector and constraints in linear programs.
Optimal Control Theory optimizes neural networks, improving robustness and efficiency.
problem Optimizing deep neural networks (DNNs) for better performance and efficiency.
method Integrating Optimal Control Theory with Backpropagation to develop a new optimizer.
result Optimal Control Theoretic Neural Optimizer (OCNOpt) improves upon existing methods in robustness and efficiency.
Unified backpropagation improves multi-objective deep learning performance.
problem Improving classification performance in hybrid neural networks.
method Linking hybrid loss functions through unified backpropagation.
result Consistent improvements in deep convolutional neural network classification performance.
Large multilayer neural networks trained with backpropagation have recently achieved state-of-the-art results in a wide range of problems. However, using backprop for neural net learning still has some disadvantages, e.g., having to tune a large number of hyperparameters to the data, lack of calibrated probabilistic pr…
RIFLE improves deep transfer learning by reinitializing fully-connected layers.
problem Limited improvement in transfer learning accuracy with pre-trained models on small datasets.
method Re-Initializing fully-connected layers with random scratch during fine-tuning.
result Significant improvement in deep transfer learning accuracy across various datasets.
Unified framework reduces NFEs for inverse problems.
problem High computational costs and degraded reconstruction quality in existing LDM-based inverse solvers.
method Consistency Regularised Gradient Flows for posterior sampling and prompt optimization.
result Significantly reduced computational cost with state-of-the-art performance.
Backpropagation-free trunk training improves model performance on various benchmarks.
problem Memory inefficiency and noisy gradient estimates in deep network training.
method Split Forward Gradient (Split-FG) method that splits network into trunk and head, estimating only trunk gradient.
result Split-FG achieves better performance than pure forward-gradient training and backpropagation on various benchmarks.
BinaryGAN uses binary neurons for GAN training.
problem Training GANs with binary outputs.
method End-to-end backpropagation with sigmoid-adjusted straight-through estimators.
result BinaryGAN can generate binary-valued predictions.
A hybrid training method reduces SNN training time and complexity.
problem Training deep SNNs is computationally expensive and time-consuming.
method Hybrid training technique combining initialization from converted SNNs and incremental spike-timing dependent backpropagation (STDB).
result The method converges in less than 20 epochs, reducing training complexity and time.
Probabilistic models with discrete latent variables naturally capture datasets composed of discrete classes. However, they are difficult to train efficiently, since backpropagation through discrete variables is generally not possible. We present a novel method to train a class of probabilistic models with discrete late…