A major drawback of backpropagation through time (BPTT) is the difficulty of learning long-term dependencies, coming from having to propagate credit information backwards through every single step of the forward computation. This makes BPTT both computationally impractical and biologically implausible. For this reason,…
On-device research index
arXiv research
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.
168,695 papers · 148 categories
Trend · papers per month
48 results for “Backpropagation Through Time”
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.
Neural network learning is usually time-consuming since backpropagation needs to compute full gradients and backpropagate them across multiple layers. Despite its success of existing works in accelerating propagation through sparseness, the relevant theoretical characteristics remain under-researched and empirical stud…
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.
Truncated backpropagation through time (TBPTT) is a popular method for learning in recurrent neural networks (RNNs) that saves computation and memory at the cost of bias by truncating backpropagation after a fixed number of lags. In practice, choosing the optimal truncation length is difficult: TBPTT will not converge …
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.
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.
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.
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.
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.
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.
This paper proposes an in-depth re-thinking of neural computation that parallels apparently unrelated laws of physics, that are formulated in the variational framework of the least action principle. The theory holds for neural networks that are also based on any digraph, and the resulting computational scheme exhibits …
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…
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.
Despite recent advances in training recurrent neural networks (RNNs), capturing long-term dependencies in sequences remains a fundamental challenge. Most approaches use backpropagation through time (BPTT), which is difficult to scale to very long sequences. This paper proposes a simple method that improves the ability …
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.
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.
In real-world scenarios, it is appealing to learn a model carrying out stochastic operations internally, known as stochastic computation graphs (SCGs), rather than learning a deterministic mapping. However, standard backpropagation is not applicable to SCGs. We attempt to address this issue from the angle of cost propa…
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.
We consider time-domain digital backpropagation with chromatic dispersion filters jointly optimized and quantized using machine-learning techniques. Compared to the baseline implementations, we show improved BER performance and >40% power dissipation reductions in 28-nm CMOS.
We propose Sideways, an approximate backpropagation scheme for training video models. In standard backpropagation, the gradients and activations at every computation step through the model are temporally synchronized. The forward activations need to be stored until the backward pass is executed, preventing inter-layer …
Many transformations in deep learning architectures are sparsely connected. When such transformations cannot be designed by hand, they can be learned, even through plain backpropagation, for instance in attention mechanisms. However, during learning, such sparse structures are often represented in a dense form, as we d…
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.
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.
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.
Most successful machine intelligence systems rely on gradient-based learning, which is made possible by backpropagation. Some systems are designed to aid us in interpreting data when explicit goals cannot be provided. These unsupervised systems are commonly trained by backpropagating through a likelihood function. We i…
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.
In recent years, the mean field theory has been applied to the study of neural networks and has achieved a great deal of success. The theory has been applied to various neural network structures, including CNNs, RNNs, Residual networks, and Batch normalization. Inevitably, recent work has also covered the use of dropou…
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.
We propose a low-complexity sub-banded DSP architecture for digital backpropagation where the walk-off effect is compensated using simple delay elements. For a simulated 96-Gbaud signal and 2500 km optical link, our method achieves a 2.8 dB SNR improvement over linear equalization.
Dynamic programming (DP) solves a variety of structured combinatorial problems by iteratively breaking them down into smaller subproblems. In spite of their versatility, DP algorithms are usually non-differentiable, which hampers their use as a layer in neural networks trained by backpropagation. To address this issue,…
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…
Given a set of observations generated by an optimization process, the goal of inverse optimization is to determine likely parameters of that process. We cast inverse optimization as a form of deep learning. Our method, called deep inverse optimization, is to unroll an iterative optimization process and then use backpro…
To address the challenge of backpropagating the gradient through categorical variables, we propose the augment-REINFORCE-swap-merge (ARSM) gradient estimator that is unbiased and has low variance. ARSM first uses variable augmentation, REINFORCE, and Rao-Blackwellization to re-express the gradient as an expectation und…
Learning long-term dependencies is a key long-standing challenge of recurrent neural networks (RNNs). Hierarchical recurrent neural networks (HRNNs) have been considered a promising approach as long-term dependencies are resolved through shortcuts up and down the hierarchy. Yet, the memory requirements of Truncated Bac…
SparseProp speeds up SNN simulations and training by four orders of magnitude.
problem Efficiently simulating and training large spiking neural networks.
method Event-based algorithm that reduces computational cost from O(N) to O(log(N)) per spike.
result Numerically exact simulations of large spiking networks and efficient training using backpropagation.
We present a general framework for training deep neural networks without backpropagation. This substantially decreases training time and also allows for construction of deep networks with many sorts of learners, including networks whose layers are defined by functions that are not easily differentiated, like decision t…
LLT-ECG classifies ECG signals without backpropagation using linear laws.
problem ECG signal classification efficiency and verifiability.
method Forward linear law identification for ECG signal features.
result State-of-the-art performance on real-world ECG datasets.
This paper proposes a method for machine learning from unlabeled data in the form of a time-series. The mapping that is learned is shown to extract slowly evolving information that would be useful for control applications, while efficiently filtering out unwanted, higher-frequency noise. The method consists of training…
Teaches matrix calculus for machine learning and optimization.
problem Computing derivatives of functions involving matrices.
method Extends differential calculus to vector spaces, focusing on practical applications in machine learning.
result Introduction of adjoint and reverse-mode differentiation for efficient computation.
FlowChef steers RFMs to efficiently guide image generation tasks.
problem Efficiently guiding image generation tasks with RFMs.
method Developed a theoretical and empirical understanding of RFMs' vector field dynamics, proposing FlowChef for gradient-free navigation.
result FlowChef significantly outperforms baselines in performance, memory, and time requirements.