A novel memory network improves interpretability and training for EHR analysis.
problem Limited interpretability and training difficulty in traditional memory networks for EHR analysis.
method Proposes a hybrid memory architecture with explicit and blurred memory blocks for improved interpretability and training efficiency.
result The model performs comparably to state-of-the-art methods and enables ready interpretation of results.
Tensor models decode human perception and memory using SPO triples.
problem Understanding implicit and explicit perception and memory in the brain.
method Tensor models with SPO triples, dual representations, and four layers.
result Semantic memory is crucial for explicit perception and declarative memories.
Efficient echo state network with explicit memory performs well on benchmark tasks.
problem Training differentiable neural computers is difficult and time-consuming.
method Echo state network with an explicit memory.
result Echo state network can recognize all regular languages, including those contractive networks cannot.
We investigate the robustness properties of image recognition models equipped with two features inspired by human vision, an explicit episodic memory and a shape bias, at the ImageNet scale. As reported in previous work, we show that an explicit episodic memory improves the robustness of image recognition models agains…
New method achieves superlinear convergence rate with limited memory.
problem Achieving superlinear convergence rate in quasi-Newton methods with limited memory.
method Limited-memory Greedy BFGS (LG-BFGS) method with displacement aggregation and basis vector selection.
result Explicit non-asymptotic superlinear convergence rate demonstrated.
Memory networks are neural networks with an explicit memory component that can be both read and written to by the network. The memory is often addressed in a soft way using a softmax function, making end-to-end training with backpropagation possible. However, this is not computationally scalable for applications which …
Deep networks retain initial bias after training, affecting generalization.
problem Understanding how much initial bias in neural networks survives training.
method Introduced initialization memory to measure initial bias's survival.
result SGD can preserve initial bias, while Adam-family methods erase it.
We propose an explicit recursive method to approximate a power-law with a finite sum of weighted exponentials. Applications to moving averages with long memory are discussed in relationship with stochastic volatility models.
NEST optimizes deep learning training by placing devices efficiently across networks and memory.
problem Inefficient device placement in distributed deep learning leads to high communication and memory overhead.
method NEST uses network-, compute-, and memory-aware dynamic programming to optimize device placement.
result NEST achieves up to 2.43 times higher throughput and better memory efficiency.
We give explicit representation formulas for marginally trapped submanifolds of co-dimension two in pseudo-Riemannian spaces with arbitrary signature and constant sectional curvature. This paper is dedicated to the memory of Franki Dillen, 1963-2013.
V-HMN integrates memory mechanisms for improved image recognition.
problem Limited interpretability and high data requirements of existing vision backbones.
method Brain-inspired hierarchical memory modules with iterative refinement.
result V-HMN achieves strong performance on image classification benchmarks.
Develops hyperparameter transfer methods for Dense Associative Memories.
problem Challenges in transferring hyperparameters for DenseAMs due to unique architecture and activation functions.
method Derives explicit prescriptions for hyperparameter transfer from small to large models.
result Excellent agreement between theoretical and empirical results.
A new framework for efficient sequence maps using Bayesian filtering and covariance.
problem Designing efficient recurrent sequence maps from explicit memory assumptions.
method Design-model framework, exact Bayesian filtering, query-dependent readout, linear-Gaussian instantiation.
result Improved robustness and retrieval performance across various benchmarks.
Investment decisions can benefit from incorporating an accumulated knowledge of the past to drive future decision making. We introduce Continual Learning Augmentation (CLA) which is based on an explicit memory structure and a feed forward neural network (FFNN) base model and used to drive long term financial investment…
Investor optimizes investment timing with future knowledge, overcoming transaction costs.
problem Optimal investment timing with future peeking, constrained by transaction costs.
method Solves control problem with infinite-dimensional memory using Gaussian Volterra integral equations.
result Explicit solution to optimal investment problem in Bachelier setting.
Implicit models can match or exceed explicit models with more test-time compute.
problem Understanding the expressive power and scaling of implicit models.
method Nonparametric analysis of expressive power, mathematical characterization of implicit operators, and test-time scaling experiments.
result Implicit models can progressively express more complex mappings through iteration, matching a richer function class with test-time compute.
GMED edits stored examples to improve continual learning.
problem Catastrophic forgetting in task-free continual learning.
method Gradient-based memory editing of stored examples.
result GMED-edited examples help prevent forgetting.
Dynamic memory prevents forgetting in continuous learning of medical images.
problem Catastrophic forgetting in machine learning models over time due to domain shifts.
method Dynamic memory to store and replay diverse training data subsets.
result Dynamic memory mitigates forgetting without knowing when shifts occur.
A new memory-based fusion layer improves multi-modal deep learning performance.
problem Improving performance of multi-modal deep learning by addressing long-term dependencies.
method Introducing a Memory based Attentive Fusion (MBAF) layer that incorporates both current and long-term dependencies.
result The MBAF layer enhances fusion and improves performance across different modalities and networks.
Spot option prices, forwards and options on forwards relevant for the commodity markets are computed when the underlying process S is modelled as an exponential of a process ξ with memory as e.g. a Lévy semi-stationary process. Moreover a risk premium \r{ho} representing storage costs, illiquidity, convenience yield or…
New algorithms solve convex optimization problems with limited memory.
problem Solving convex optimization problems with constrained memory.
method Recursive cutting-plane algorithms dividing variables into blocks.
result Achieves optimal memory usage and oracle complexity in certain regimes.
Personalized predictive medicine necessitates the modeling of patient illness and care processes, which inherently have long-term temporal dependencies. Healthcare observations, recorded in electronic medical records, are episodic and irregular in time. We introduce DeepCare, an end-to-end deep dynamic neural network t…
New model controls memory in seq2seq tasks, revealing learning regimes.
problem Understanding memory in seq2seq tasks using neural networks.
method Introducing a stochastic switching-Ornstein-Uhlenbeck (SSOU) model to control memory and a measure of non-Markovianity.
result Two learning regimes emerge from the interplay of time scales in the SSOU process.
METEOR learns efficient representations from multi-modal data streams.
problem Efficiently interpreting multi-modal information in complex environments.
method METEOR learns compact representations by sharing parameters within semantically meaningful groups and preserving domain-agnostic semantics.
result METEOR reduces memory usage by around 80% compared to conventional methods.
Deep reinforcement learning algorithms have recently been used to train multiple interacting agents in a centralised manner whilst keeping their execution decentralised. When the agents can only acquire partial observations and are faced with tasks requiring coordination and synchronisation skills, inter-agent communic…
This paper provides a mathematical framework for time-delay reservoir computing.
problem Lack of rigorous mathematical foundations for reservoir computing properties.
method Control-theoretic framework, formal definitions of separation and fading memory, explicit lower bound derivation.
result Established formal definitions and connections to stability notions for time-delay systems.
Adaptive beamforming collapses in highly non-stationary environments, but the Universal Switching Beamformer resolves this by dynamically adjusting memory length.
problem Adaptive beamforming performance degrades in highly non-stationary environments.
method Integrating sequential prediction into the beamforming architecture.
result The USB achieves agility and precision in tracking highly non-stationary scenes.
Self-referential meta learning avoids explicit optimization by modifying itself.
problem Dependency on human engineering in meta learning algorithms.
method Investigates self-referential meta learning systems that modify themselves without explicit optimization.
result Self-referential neural networks can improve their own modifications without explicit optimization.
Dense Associative Memories outperform classical networks in robustness and signal processing.
problem Improving neural network performance in adversarial attacks and weak signal processing.
method Relaxing replica symmetry in statistical mechanics of spin glasses to analyze unsupervised and supervised learning.
result Explicit analytical investigation of phase diagrams and storage capacities for Dense Associative Memories.
The Sinkhorn "distance", a variant of the Wasserstein distance with entropic regularization, is an increasingly popular tool in machine learning and statistical inference. However, the time and memory requirements of standard algorithms for computing this distance grow quadratically with the size of the data, making th…
The study proves necessary conditions for robust decision-making in uncertain environments.
problem Conditions for robust decision-making in uncertain environments.
method Quantitative selection theorems and binary betting decisions.
result World models, belief-like memory, and persistent variables are necessary for strong task performance.
Recurrent neural networks (RNNs) have drawn interest from machine learning researchers because of their effectiveness at preserving past inputs for time-varying data processing tasks. To understand the success and limitations of RNNs, it is critical that we advance our analysis of their fundamental memory properties. W…
Modern deep learning-based recommendation systems exploit hundreds to thousands of different categorical features, each with millions of different categories ranging from clicks to posts. To respect the natural diversity within the categorical data, embeddings map each category to a unique dense representation within a…
New theorems show agents need specific internal structures to perform well under uncertainty.
problem How do agents need to be structured to perform well under uncertainty?
method Proved selection theorems showing strong task performance forces specific internal structures.
result Strong task performance forces world models, belief-like memory, and persistent regime-tracking variables.
This paper improves radar performance against jammers using RL.
problem Improving radar performance against jammers.
method Reinforcement Learning (RL) with Deep Q-Network (DQN) and Long Short Term Memory (LSTM) networks.
result Softmax operator improves RL algorithm performance.
Transformers learn to solve various tasks without explicit design.
problem Training models with minimal inductive bias.
method Meta-learning approach to train general-purpose in-context learning algorithms.
result Transformers can be meta-trained to solve a wide range of tasks.
Solves TOD systems' query annotation problem without explicit annotations.
problem Training TOD systems without explicit KB query annotation.
method Reinforcement learning (RL) and pipelined approach for query prediction and system training.
result Improved RL agent with modifications for TOD tasks.
Improved neural-ODE for faster convergence and stability.
problem Stability, consistency, and convergence issues in neural-ODE solvers.
method Proposed a first-order Nesterov's accelerated gradient (NAG) based ODE-solver.
result Efficacy demonstrated in three tasks: supervised classification, density estimation, and time-series modelling.
Scalable PnP-ADMM for large-scale imaging problems.
problem Heavy computational and memory requirements of current PnP algorithms.
method Incremental variant of PnP-ADMM with theoretical convergence guarantees.
result Fast convergence and scalability compared to existing PnP algorithms.
In model-based reinforcement learning, generative and temporal models of environments can be leveraged to boost agent performance, either by tuning the agent's representations during training or via use as part of an explicit planning mechanism. However, their application in practice has been limited to simplistic envi…
New method SF-AdamW trains large models without decay phases or memory overhead.
problem Inadequate fixed compute budgets for large-scale training.
method Schedule-Free (SF) method revisited and refined.
result SF-AdamW effectively navigates loss landscape without decay phases or memory overhead.
New explanation of reservoir computing using random projections.
problem Understanding the randomness in reservoir computing.
method Constructing strongly universal reservoir systems as random projections of state-space systems.
result Approximation of any fading memory filters class by training a linear readout for each filter.
Proposes a novel SAM operator for separate item and relational memories.
problem Limited memory interactions in neural networks.
method Introduces a Self-attentive Associative Memory (SAM) operator to separate item and relational memories.
result Achieves competitive results in various tasks, including geometry, graph, reinforcement learning, and question answering.
ADSGD method speeds up model identification in sparse optimization.
problem Implicit model identification in sparse optimization problems.
method Accelerated Doubly Stochastic Gradient Method (ADSGD) for faster explicit model identification.
result ADSGD achieves faster explicit model identification and improved algorithm efficiency.
Kernel approximation methods create explicit, low-dimensional kernel feature maps to deal with the high computational and memory complexity of standard techniques. This work studies a supervised kernel learning methodology to optimize such mappings. We utilize the Discriminant Information criterion, a measure of class …
In this paper, we propose a dual memory structure for reinforcement learning algorithms with replay memory. The dual memory consists of a main memory that stores various data and a cache memory that manages the data and trains the reinforcement learning agent efficiently. Experimental results show that the dual memory …
Improved SVD for shifted matrices without explicit matrix construction.
problem Efficiently estimating SVD of shifted matrices.
method Shifted Randomized SVD algorithm.
result More efficient matrix factorization and low-rank approximation.
New method reduces memory usage for high-dimensional variable selection.
problem Scalability issues in high-dimensional variable selection, especially in genomics.
method Adaptive sampling of null features to eliminate dummy matrix materialization.
result Reduces memory and runtime by several orders of magnitude while preserving FDR control.