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.
FF layers in transformers are nearly as interpretable as sparse autoencoders.
Can machines trace human knowledge like humans? Knowledge tracing (KT) is a fundamental task in a wide range of applications in education, such as massive open online courses (MOOCs), intelligent tutoring systems, educational games, and learning management systems. It models dynamics in a student's knowledge states in …
OSA overcomes instability in skipless Transformers.
New algorithm reduces costs and latency for large language model inference.
Service-induced congestion in memory-constrained LLM serving
Deep reinforcement learning techniques have demonstrated superior performance in a wide variety of environments. As improvements in training algorithms continue at a brisk pace, theoretical or empirical studies on understanding what these networks seem to learn, are far behind. In this paper we propose an interpretable…
Linear memory stores associations up to a logarithmic scale, but listwise retrieval can handle a quadratic scale.
Recent student knowledge modeling algorithms such as Deep Knowledge Tracing (DKT) and Dynamic Key-Value Memory Networks (DKVMN) have been shown to produce accurate predictions of problem correctness within the same learning system. However, these algorithms do not attempt to directly infer student knowledge. In this pa…
Deep learning based knowledge tracing model has been shown to outperform traditional knowledge tracing model without the need for human-engineered features, yet its parameters and representations have long been criticized for not being explainable. In this paper, we propose Deep-IRT which is a synthesis of the item res…
Training large-scale image recognition models is computationally expensive. This raises the question of whether there might be simple ways to improve the test performance of an already trained model without having to re-train or fine-tune it with new data. Here, we show that, surprisingly, this is indeed possible. The …
FibQuant improves KV-cache compression for long-context inference.
Tensor factorization is a powerful tool to analyse multi-way data. Compared with traditional multi-linear methods, nonlinear tensor factorization models are capable of capturing more complex relationships in the data. However, they are computationally expensive and may suffer severe learning bias in case of extreme dat…
Improved stock price prediction using attention modules and news sentiment.
Knowledge tracing is the task of modeling each student's mastery of knowledge concepts (KCs) as (s)he engages with a sequence of learning activities. Each student's knowledge is modeled by estimating the performance of the student on the learning activities. It is an important research area for providing a personalized…
A new graph encoder StarE models hyper-relational KGs, improving link prediction.
FEM improves attention mechanisms by applying value-driven log-linear tilts.
Quantum self-attention boosts automated market maker performance in crypto trading.
GTA improves transformer-based NVS models by encoding geometric structure.
OLS predictions are shown to be similar to attention mechanisms in models.
Heretofore, neural networks with external memory are restricted to single memory with lossy representations of memory interactions. A rich representation of relationships between memory pieces urges a high-order and segregated relational memory. In this paper, we propose to separate the storage of individual experience…
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 …
Stable Hadamard Memory improves reinforcement learning by efficiently managing memory.
New memory allocation scheme improves image generation performance.
DAM with MRL improves relational reasoning in MANNs.
New bounds adaptively control spectral complexity of trained Transformers.
We discuss memory models which are based on tensor decompositions using latent representations of entities and events. We show how episodic memory and semantic memory can be realized and discuss how new memory traces can be generated from sensory input: Existing memories are the basis for perception and new memories ar…
mGRN improves multivariate time series prediction by managing marginal and joint memories.
Model combines long-term and short-term memory using conceptors.
Learning to remember long sequences remains a challenging task for recurrent neural networks. Register memory and attention mechanisms were both proposed to resolve the issue with either high computational cost to retain memory differentiability, or by discounting the RNN representation learning towards encoding shorte…
In recent years, memory-augmented neural networks(MANNs) have shown promising power to enhance the memory ability of neural networks for sequential processing tasks. However, previous MANNs suffer from complex memory addressing mechanism, making them relatively hard to train and causing computational overheads. Moreove…
Enhanced Hopfield model boosts memory retrieval capacity.
Current generation of memory-augmented neural networks has limited scalability as they cannot efficiently process data that are too large to fit in the external memory storage. One example of this is lifelong learning scenario where the model receives unlimited length of data stream as an input which contains vast majo…
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 …
New Bol operators found for supermanifolds with specific dimensions.
Memory-constrained algorithms need superlinear memory for efficient convex optimization.
We present an end-to-end trained memory system that quickly adapts to new data and generates samples like them. Inspired by Kanerva's sparse distributed memory, it has a robust distributed reading and writing mechanism. The memory is analytically tractable, which enables optimal on-line compression via a Bayesian updat…
Generative diffusion models mimic biological memory networks, encoding associative dynamics in deep neural weights.
A new model for sequential memory using temporal predictive coding.
We augment recurrent neural networks with an external memory mechanism that builds upon recent progress in metalearning. We conceptualize this memory as a rapidly adaptable function that we parameterize as a deep neural network. Reading from the neural memory function amounts to pushing an input (the key vector) throug…
Accelerators with power-law memory are proposed in the framework of the discrete time approach. To describe discrete accelerators we use the capital stock adjustment principle, which has been suggested by Matthews.The suggested discrete accelerators with memory describe the economic processes with the power-law memory …
A new memory system handles non-stationary environments by self-sizing and retaining memories.
Paper questions RNN and LSTM's long-term memory and introduces a new definition.
Deep learning typically requires training a very capable architecture using large datasets. However, many important learning problems demand an ability to draw valid inferences from small size datasets, and such problems pose a particular challenge for deep learning. In this regard, various researches on "meta-learning…
Neural networks powered with external memory simulate computer behaviors. These models, which use the memory to store data for a neural controller, can learn algorithms and other complex tasks. In this paper, we introduce a new memory to store weights for the controller, analogous to the stored-program memory in modern…
Augmenting a neural network with memory that can grow without growing the number of trained parameters is a recent powerful concept with many exciting applications. We propose a design of memory augmented neural networks (MANNs) called Labeled Memory Networks (LMNs) suited for tasks requiring online adaptation in class…
We study the long-term memory in diverse stock market indices and foreign exchange rates using the Detrended Fluctuation Analysis(DFA). For all daily and high-frequency market data studied, no significant long-term memory property is detected in the return series, while a strong long-term memory property is found in th…
New memory effect discovered in gravitational wave behavior.
Memory is increasingly often the bottleneck when training neural network models. Despite this, techniques to lower the overall memory requirements of training have been less widely studied compared to the extensive literature on reducing the memory requirements of inference. In this paper we study a fundamental questio…