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.
Study finds reinforcement learning performance plateaus due to environmental interference.
New measure of interference helps understand and mitigate learning issues in reinforcement learning.
To survive in the dynamically-evolving world, we accumulate knowledge and improve our skills based on experience. In the process, gaining new knowledge does not disrupt our vigilance to external stimuli. In other words, our learning process is 'accumulative' and 'online' without interruption. However, despite the recen…
Modern deep neural networks are well known to be brittle in the face of unknown data instances and recognition of the latter remains a challenge. Although it is inevitable for continual-learning systems to encounter such unseen concepts, the corresponding literature appears to nonetheless focus primarily on alleviating…
Catastrophic forgetting/interference is a critical problem for lifelong learning machines, which impedes the agents from maintaining their previously learned knowledge while learning new tasks. Neural networks, in particular, suffer plenty from the catastrophic forgetting phenomenon. Recently there has been several eff…
Gradient-based meta-learning has proven to be highly effective at learning model initializations, representations, and update rules that allow fast adaptation from a few samples. The core idea behind these approaches is to use fast adaptation and generalization -- two second-order metrics -- as training signals on a me…
Current training regimes for deep learning usually involve exposure to a single task / dataset at a time. Here we start from the observation that in this context the trained model is not given any knowledge of anything outside its (single-task) training distribution, and has thus no way to learn parameters (i.e., featu…
Adam optimizer leads to more forgetting in neural networks.
Sparse representations have been shown to be useful in deep reinforcement learning for mitigating catastrophic interference and improving the performance of agents in terms of cumulative reward. Previous results were based on a two step process were the representation was learned offline and the action-value function w…
Lifelong learning is the problem of learning multiple consecutive tasks in a sequential manner, where knowledge gained from previous tasks is retained and used to aid future learning over the lifetime of the learner. It is essential towards the development of intelligent machines that can adapt to their surroundings. I…
A new method learns from multi-modal sequences with external memory.
New insights into neural network forgetting reveal a trade-off between node activation and re-use.
Sparse routing networks with co-training prevent catastrophic forgetting in continual learning.
Modulating masks improve lifelong reinforcement learning.
Lifelong learning is a very important step toward realizing robust autonomous artificial agents. Neural networks are the main engine of deep learning, which is the current state-of-the-art technique in formulating adaptive artificial intelligent systems. However, neural networks suffer from catastrophic forgetting when…
Study shows how task similarity affects forgetting in teacher-student setup.
We explore the behavior of a standard convolutional neural net in a continual-learning setting that introduces visual classification tasks sequentially and requires the net to master new tasks while preserving mastery of previously learned tasks. This setting corresponds to that which human learners face as they acquir…
New insights into continual learning with task similarity.
Artificial neural networks face the well-known problem of catastrophic forgetting. What's worse, the degradation of previously learned skills becomes more severe as the task sequence increases, known as the long-term catastrophic forgetting. It is due to two facts: first, as the model learns more tasks, the intersectio…
Pseudo-rehearsal allows neural networks to learn a sequence of tasks without forgetting how to perform in earlier tasks. Preventing forgetting is achieved by introducing a generative network which can produce data from previously seen tasks so that it can be rehearsed along side learning the new task. This has been fou…
TMNs model brain memory systems for continual learning.
La-MAML improves fast online continual learning with a look-ahead approach.
SpaceNet improves continual learning by intelligently compressing neural connections.
Humans and animals have the ability to continually acquire, fine-tune, and transfer knowledge and skills throughout their lifespan. This ability, referred to as lifelong learning, is mediated by a rich set of neurocognitive mechanisms that together contribute to the development and specialization of our sensorimotor sk…
New method removes interference bias in causal models.
Proposes Mv-TCNN for continual learning without known tasks in advance.
Estimates causal effects in networks with varying interference.
TD learning reduces interference, leading to better generalization.
Deep learning (DL) based autoencoder has shown great potential to significantly enhance the physical layer performance. In this paper, we present a DL based autoencoder for interference channel. Based on a characterization of a k-user Gaussian interference channel, where the interferences are classified as different le…
After learning a concept, humans are also able to continually generalize their learned concepts to new domains by observing only a few labeled instances without any interference with the past learned knowledge. In contrast, learning concepts efficiently in a continual learning setting remains an open challenge for curr…
New method prevents forgetting in LLMs by dynamically identifying task-specific subspaces.
The paper addresses Qini curve estimation under clustered network interference.
Sequential learning of multiple tasks in artificial neural networks using gradient descent leads to catastrophic forgetting, whereby previously learned knowledge is erased during learning of new, disjoint knowledge. Here, we propose a new approach to sequential learning which leverages the recent discovery of adversari…
Paper predicts interference for better LA in URLLC.
This work addresses causal inference challenges in networked interference and proposes GNN-based estimators for individual treatment effects.
DN estimator mitigates network interference in experiments.
Study efficient inference for network quantile causal effects with partial interference.
Spatial Deconfounder tackles interference and confounding in spatial data.
Algorithm learns interference network and optimizes treatment allocation for unknown network effects.
Bayesian method estimates causal effects with proxy networks.
A continual learning agent should be able to build on top of existing knowledge to learn on new data quickly while minimizing forgetting. Current intelligent systems based on neural network function approximators arguably do the opposite---they are highly prone to forgetting and rarely trained to facilitate future lear…
Machine learning method characterizes network interference in A/B tests.
FRONT optimizes decisions with interference, reducing regret over time.
The paper tackles adaptive targeting in networks with interference effects.
This article proposes and evaluates a technique to predict the level of interference in wireless networks. We design a recursive predictor that estimates future interference values by filtering measured interference at a given location. The predictor's parameterization is done offline by translating the autocorrelation…
New algorithm optimizes interventions under network interference, scaling to large networks.
We investigate sparse representations for control in reinforcement learning. While these representations are widely used in computer vision, their prevalence in reinforcement learning is limited to sparse coding where extracting representations for new data can be computationally intensive. Here, we begin by demonstrat…
A new method reduces task interference in model merging.