Paper introduces a technique to simplify RNN policies for better understanding and analysis.
problem Difficulty in explaining and analyzing RNN policies due to continuous-valued memory vectors and observation features.
method Quantized Bottleneck Insertion technique to learn finite representations of RNN vectors and features.
result Finite representations of RNN policies can be as small as 3 discrete memory states and 10 observations, improving interpretability.
Representing a dialog policy as a recurrent neural network (RNN) is attractive because it handles partial observability, infers a latent representation of state, and can be optimized with supervised learning (SL) or reinforcement learning (RL). For RL, a policy gradient approach is natural, but is sample inefficient. I…
New method learns adaptive exploration strategies for dynamic tasks.
problem Learning effective exploration strategies in changing environments.
method Informed policy regularization to reduce sample complexity of RNN-based policies.
result Method learns efficient exploration strategies balancing information gathering and reward maximization.
This paper proposes a method for estimating the effect of a policy intervention on an outcome over time. We train recurrent neural networks (RNNs) on the history of control unit outcomes to learn a useful representation for predicting future outcomes. The learned representation of control units is then applied to the t…
Solves POMDPs with recurrent neural networks and natural policy gradient.
problem Non-stationarity in optimal policies of POMDPs.
method Integrates recurrent neural networks into natural policy gradient and temporal difference learning.
result Non-asymptotic theoretical guarantees for global optimality up to function approximation.
AC-RNN improves RNN for sequence labeling tasks.
problem RNN's exposure bias in maximum-likelihood training.
method Actor-Critic training for RNNs.
result AC-RNN outperforms CRF on NER and CCG tagging.
Efficient neural architecture search by sampling structure and operations.
problem Efficiently searching for optimal neural architectures.
method Decouples structure and operation search, using reinforcement learning with policy vectors.
result Significantly improved efficiency compared to traditional methods.
Simulates sepsis treatment decisions using a world model approach.
problem Predicting optimal sepsis treatment actions based on noisy EHR data.
method Uses a Variational Auto-Encoder and Mixture Density Network (MDN-RNN) to model sepsis patient trajectories.
result Simulator learns from MIMIC dataset to predict patient states.
IAM improves deep RL by selectively storing influential past observations.
problem Training and performance issues with recurrent neural networks in high-dimensional environments.
method Influence-aware memory architecture that restricts input to variables influencing hidden state.
result IAM outperforms standard RNNs in training speed and policy performance.
Hybrid model improves COVID-19 case forecasting accuracy.
problem Limited data and simplistic models for accurate prediction.
method Combining SEIR and RNN on a graph structure with local and edge features.
result Improves prediction accuracy on state-level COVID-19 data.
Dynamic treatment recommendation systems based on large-scale electronic health records (EHRs) become a key to successfully improve practical clinical outcomes. Prior relevant studies recommend treatments either use supervised learning (e.g. matching the indicator signal which denotes doctor prescriptions), or reinforc…
Delayed-RNN approximates stacked and bidirectional RNNs.
problem Improving RNN expressiveness and representational capacity.
method Weight-constrained delayed-RNN, equivalent to stacked-RNNs, with partial acausality.
result Delayed-RNN can approximate stacked and bidirectional RNNs, outperforming them in some tasks.
Paper clusters event sequences using a reinforcement learning approach with policy mixture model.
problem Clustering event sequences with varying temporal patterns.
method Reinforcement learning with a policy mixture model, decomposing sequences into states and actions.
result Effective clustering of event sequences into underlying policies, outperforming existing methods.
Recurrent Neural Networks (RNNs) are powerful sequence modeling tools. However, when dealing with high dimensional inputs, the training of RNNs becomes computational expensive due to the large number of model parameters. This hinders RNNs from solving many important computer vision tasks, such as Action Recognition in …
PF-RNNs use particle filtering to model uncertainty in RNNs for better sequential data prediction.
problem Highly variable and noisy sequential data.
method PF-RNNs maintain a latent state distribution as a set of particles, updating with Bayes rule.
result PF-RNNs outperform standard RNNs on various sequence prediction tasks.
In this paper, we explore different ways to extend a recurrent neural network (RNN) to a \textit{deep} RNN. We start by arguing that the concept of depth in an RNN is not as clear as it is in feedforward neural networks. By carefully analyzing and understanding the architecture of an RNN, however, we find three points …
Recurrent Neural Networks (RNNs) with attention mechanisms have obtained state-of-the-art results for many sequence processing tasks. Most of these models use a simple form of encoder with attention that looks over the entire sequence and assigns a weight to each token independently. We present a mechanism for focusing…
This paper studies a theoretical pruning method for RNNs to reduce computational costs.
problem High computational costs in recurrent neural networks (RNNs).
method Spectral pruning inspired approach for RNNs.
result Generalization error bounds for compressed RNNs are provided.
Lyapunov analysis improves RNN performance prediction.
problem Uncertainty in RNN performance prediction due to hyperparameters and architecture.
method Lyapunov spectral analysis of RNNs and Autoencoder-Lyapunov Embedding Learning (AeLLE).
result AeLLE successfully correlates RNN Lyapunov spectrum with accuracy and predicts performance.
In this work, we propose a novel recurrent neural network (RNN) architecture. The proposed RNN, gated-feedback RNN (GF-RNN), extends the existing approach of stacking multiple recurrent layers by allowing and controlling signals flowing from upper recurrent layers to lower layers using a global gating unit for each pai…
Proposes Fusion Recurrent Neural Network for sequence data.
problem Improving sequence learning for practical applications.
method Fusion module and Transport module for sequence data.
result Fusion RNN performs comparably to state-of-the-art RNNs.
Paper uses AI for more efficient hedging of financial options.
problem Inefficient hedging in financial models.
method RL agents and GANs for delta hedging.
result RL-based hedging outperforms classic models in Q-world.
Recurrent neural networks (RNNs) are powerful and effective for processing sequential data. However, RNNs are usually considered "black box" models whose internal structure and learned parameters are not interpretable. In this paper, we propose an interpretable RNN based on the sequential iterative soft-thresholding al…
Efficient RNN algorithm guarantees convergence in online learning.
problem Online nonlinear regression with RNNs.
method First-order training algorithm with convergence guarantee.
result The algorithm converges to optimum network parameters.
While Recurrent Neural Networks (RNNs) are famously known to be Turing complete, this relies on infinite precision in the states and unbounded computation time. We consider the case of RNNs with finite precision whose computation time is linear in the input length. Under these limitations, we show that different RNN va…
Paper compresses RNNs for resource-constrained devices.
problem Difficulty deploying RNNs on resource-constrained devices.
method Uses Kronecker product (KP) to compress RNN layers.
result KP compresses RNN layers by 16-38x with minimal accuracy loss.
RNNs struggle with in-context retrieval, while Transformers excel.
problem In-context retrieval capability of RNNs.
method Theoretical analysis and experimental techniques (CoT, RAG, Transformer layer).
result Enhancing RNNs with techniques improves their in-context retrieval capability, closing the representation gap with Transformers.
GPU-optimized ES-RNN boosts time series forecasting speed by 322x.
problem Efficiently forecasting time series data.
method Vectorized GPU implementation of ES-RNN.
result Up to 322x speedup in training time.
Paper refines RNN training by analyzing smoothness and attractors.
problem Exploding and vanishing gradients in RNNs.
method Refined concept of exploding gradients using cost function smoothness.
result RNNs need to learn attractors to fully use their power.
Novel method improves training RNNs by accelerating gradient descent.
problem Vanishing and exploding gradient problems in RNNs training.
method Adaptive stochastic Nesterov accelerated quasi-Newton method.
result Improved performance in training RNNs with low per-iteration cost.
Analyzes RNNs using ODEs to map their properties and improve stability.
problem Understanding and improving the stability of RNNs.
method Relates RNNs to ODEs, mapping their properties to integration methods.
result Establishes sufficient conditions for RNN training stability and designs new architectures.
Elman-type RNNs converge to globally optimal solutions in the mean-field regime.
problem Optimizing feature learning in wide RNNs.
method Analysis of gradient descent dynamics and mean-field limits.
result Fixed points of infinite-width dynamics are globally optimal.
Deep neural networks have shown promising results for various clinical prediction tasks such as diagnosis, mortality prediction, predicting duration of stay in hospital, etc. However, training deep networks -- such as those based on Recurrent Neural Networks (RNNs) -- requires large labeled data, high computational res…
Recurrent Neural Networks (RNNs) have long been recognized for their potential to model complex time series. However, it remains to be determined what optimization techniques and recurrent architectures can be used to best realize this potential. The experiments presented take a deep look into Hessian free optimization…
New kernels boost RNN performance on non-time-series data.
problem Improving performance of RNNs on non-time-series data.
method Extended RNN kernels to complex architectures, developed fast GPU implementation.
result RNN-based classifiers outperform baselines on 90 non-time-series datasets.
Lyapunov exponents help understand RNN stability.
problem Optimizing RNNs is sensitive to various parameters.
method Use Lyapunov exponents as dynamical system tools.
result Lyapunov spectrum measures training stability.
Study proves deep narrow RNNs can approximate any function, with minimum width independent of data length.
problem Proving universality of deep narrow RNNs with bounded widths.
method Analyzing RNNs as dynamical systems, proving universality for deep narrow structures with specific widths.
result Minimum width for universality of deep narrow RNNs is independent of data length.
Hamiltonian RNN controls hidden states gradient for long-term dependencies.
problem Challenges in learning long-term dependencies in RNNs.
method Symplectic discretization of Hamiltonian system to control gradient.
result Hamiltonian RNN outperforms other RNNs without hyperparameter optimization.
We introduce MinimalRNN, a new recurrent neural network architecture that achieves comparable performance as the popular gated RNNs with a simplified structure. It employs minimal updates within RNN, which not only leads to efficient learning and testing but more importantly better interpretability and trainability. We…
Frequentist method estimates uncertainty in RNNs without altering architecture.
problem Uncertainty quantification in RNNs for decision-making.
method Jackknife resampling and influence functions to estimate variability.
result The method provides theoretical coverage guarantees on uncertainty intervals.
This paper proposes structurally sparse RNNs to reduce computational and memory costs.
problem Heavy computational and memory burden in fully connected RNNs.
method Study structurally sparse RNNs, reducing recurrent operations and weights.
result Structurally sparse RNNs achieve competitive performance with reduced costs.
A new model combines spatial and spectral features for HSI classification.
problem Inefficiency and difficulty in training RNNs for HSI classification.
method Proposes St-SS-pGRU combining shorten RNN, converlusion layer, and parallel-GRU.
result Better performance and robustness in HSI classification.
New model handles uneven time intervals better than traditional methods.
problem Irregularly-sampled time series data.
method Generalizes RNNs to ODE-RNNs, explicitly modeling observation gaps.
result ODE-RNNs outperform traditional models on irregular data.
The paper proposes an algorithm to learn causal state representations for partially observable environments.
problem Learning task-agnostic state abstractions in partially observable environments.
method The approach involves learning approximate causal state representations from RNNs trained to predict observations given the history.
result The learned state representations are useful for efficient policy learning in reinforcement learning problems with rich observation spaces.
Multivariate time-series modeling and forecasting is an important problem with numerous applications. Traditional approaches such as VAR (vector auto-regressive) models and more recent approaches such as RNNs (recurrent neural networks) are indispensable tools in modeling time-series data. In many multivariate time ser…
RNNs struggle with chaotic dynamics due to exploding gradients, but we found a way to optimize training.
problem Challenging training of RNNs with chaotic dynamics due to exploding gradients.
method Relating loss gradients to Lyapunov spectrum to optimize training on chaotic data.
result RNNs with chaotic dynamics always have diverging gradients, while stable ones have bounded gradients.
RNNs are suboptimal at compressing past sensory inputs for future prediction.
problem RNNs do not optimally compress past sensory inputs for future prediction.
method Investigated RNNs trained with maximum likelihood and found they extract unnecessary information. Injected noise into hidden states to improve performance.
result Injecting noise into RNN hidden states improves predictive information, sample quality, likelihood, and classification performance.
RNNs learn combinatorial graph problems with sample complexity bounds.
problem Learning efficient approximations for real-valued combinatorial graph problems.
method Upper bounds the sample complexity for learning real-valued RNNs.
result Real-valued RNNs can be learned with polynomial number of samples.