Solves a model for sudden problem-solving ability in deep learning.
problem Emergence of new problem-solving abilities in deep learning models.
method Solves a simple multi-linear model in a skill-basis, finding analytic expressions for emergence and scaling laws.
result Simple model captures sigmoidal emergence of multiple new skills in neural networks.
Deep learning models generate languages that lack abstract reasoning.
problem Lack of abstract reasoning in deep learning-generated languages.
method Analyzed emergent language from two multi-agent games with compositional measures.
result Deep learning solutions often fail to generalize to out-of-training examples.
Noise-driven neural networks emerge modular structures, improving robustness and generalization.
problem Artificial neural networks struggle with modular solutions, leading to poor generalization and robustness.
method Inspired by brain's modular architecture, the study uses neural noise and nonlinear responses to drive the emergence of modular solutions.
result Noise-driven modularisation improves robustness and generalization in neural networks.
MPNNs generalize poorly, study reviews current research.
problem Exploring generalization abilities of MPNNs.
method Systematic review of existing literature.
result Limited understanding of MPNNs' generalization abilities.
Infants are experts at playing, with an amazing ability to generate novel structured behaviors in unstructured environments that lack clear extrinsic reward signals. We seek to replicate some of these abilities with a neural network that implements curiosity-driven intrinsic motivation. Using a simple but ecologically …
A simple model explains phase transition in large language models.
problem Understanding the emergence of abilities in large language models.
method Modeling LLM as a sequence-to-sequence random function and using a list decoder.
result A critical threshold exists where the expected number of erroneous sequences grows exponentially.
The VAE's reconstruction ability is studied using PAC-Bayes theory.
problem Understanding the performance of VAEs for unseen data.
method PAC-Bayes theory is applied to analyze VAE's reconstruction error.
result Generalization bounds on VAE's reconstruction error are provided.
Emergenet predicts animal influenza strain emergence, outperforming current methods.
problem Limited ability to quantitatively assess animal influenza strain emergence.
method Infer digital twin of sequence evolution using 220,151 HA sequences.
result Emergenet predictions outperform WHO seasonal vaccine recommendations and CDC IRAT scores.
How do we know if communication is emerging in a multi-agent system? The vast majority of recent papers on emergent communication show that adding a communication channel leads to an increase in reward or task success. This is a useful indicator, but provides only a coarse measure of the agent's learned communication a…
Investigates how neural network capacity impacts the learning of compositional languages.
problem The importance of communicative bandwidth in emergent language learning.
method Exploration of how neural network capacity affects the learning of compositional languages.
result There is a specific range of model capacity and channel bandwidth that induces compositional structure.
Neural networks learn discrete tasks on continuous data via emergent geometry.
problem Understanding how neural networks perform discrete computations on continuous data.
method Analysis of Riemannian pullback metric across neural network layers.
result Neural networks learn to discretize continuous inputs and perform logical operations on these discretized variables.
Neural networks learn task-specific features, influenced by nonlinearity.
problem Understanding the nature of task-dependent feature learning in neural networks.
method Investigation of fully-connected, wide neural networks using Bayesian framework.
result The nature of internal representations depends on neuronal nonlinearity, leading to analog, redundant, or sparse coding schemes.
New PAC-Bayes bounds use Wasserstein distances to improve generalization.
problem Lack of geometric properties in existing PAC-Bayes bounds.
method Developed new PAC-Bayes bounds with Wasserstein distances.
result Optimization guarantees translate to good generalization abilities.
New approach predicts tokens in context, explaining how ICL emerges.
problem Limited understanding of in-context learning emergence.
method Auto-regressive next-token prediction (AR-NTP) with prompt token-dependency and a two-level expectation.
result ICL emerges from the generalization of sequences and topics.
Computational swarm intelligence consists of multiple artificial simple agents exchanging information while exploring a search space. Despite a rich literature in the field, with works improving old approaches and proposing new ones, the mechanism by which complex behavior emerges in these systems is still not well und…
LaRT models LLMs' response accuracy and CoT length to evaluate reasoning ability and speed.
problem Valid evaluation of Large Language Models (LLMs) via response accuracy and chain-of-thought length.
method Introduces Latency-Response Theory (LaRT) to jointly model response accuracy and CoT length using latent ability and latent speed.
result LaRT yields higher estimation accuracy and shorter confidence intervals for latent traits compared to IRT.
Heavy-tailed distributions emerge in SGD's parameter evolution.
problem Understanding heavy-tailed distributions in SGD parameter evolution.
method Continuous diffusion approximation of SGD (homogenized SGD) analysis.
result Explicit upper and lower bounds on tail-index of homogenized SGD.
Survey examines distillation methods for large language models.
problem Efficiently compress large language models while preserving their capabilities.
method Knowledge Distillation and Dataset Distillation techniques.
result Integrating KD and DD can produce more effective and scalable compression strategies.
Nonnegative matrix factorization (NMF) is a powerful tool for data mining. However, the emergence of `big data' has severely challenged our ability to compute this fundamental decomposition using deterministic algorithms. This paper presents a randomized hierarchical alternating least squares (HALS) algorithm to comput…
Extending spatio-temporal scale limitations of models for complex atomistic systems considered in biochemistry and materials science necessitates the development of enhanced sampling methods. The potential acceleration in exploring the configurational space by enhanced sampling methods depends on the choice of collecti…
Recently the GAN generated face images are more and more realistic with high-quality, even hard for human eyes to detect. On the other hand, the forensics community keeps on developing methods to detect these generated fake images and try to guarantee the credibility of visual contents. Although researchers have develo…
Paper develops an unbiased risk estimator for learning with augmented classes.
problem Learning with augmented classes where unseen classes might appear in testing.
method Uses unlabeled training data to approximate potential distribution of augmented classes.
result Establishes an unbiased risk estimator for the testing distribution under mild assumptions.
This work tackles representation learning by introducing stochastic competition-based activations.
problem Learning diversified representations in deep learning models.
method Combining information-theoretic arguments with stochastic competition-based activations, using Stochastic Local Winner-Takes-All (LWTA) units.
result The proposed method yields significant discriminative representation learning abilities and allows for a principled investigation of intermediate network representations.
Transformers can cluster data from Gaussian mixtures without supervision.
problem Clustering data from Gaussian mixtures without labeled data.
method Theoretical analysis of attention-based layers, focusing on a simplified two-head attention layer and an identity matrix attention layer.
result Attention-based layers can align with true mixture centroids and adapt to input-specific distributions.
Study investigates how simple speech sounds can form abstract categories.
problem How do abstract categories like phonemes emerge from speech exposure?
method Used modeling techniques to test Memory-Based Learning and Error-Correction Learning.
result Error-Correction Learning models can learn abstractions, identifying phone inventory and grouping.
The challenge in controlling stochastic systems in which low-probability events can set the system on catastrophic trajectories is to develop a robust ability to respond to such events without significantly compromising the optimality of the baseline control policy. This paper presents CelluDose, a stochastic simulatio…
A model for groundwater trading among stakeholders.
problem Groundwater trading among stakeholders in a basin.
method Optimization of production by agents considering water rights, consumption, and trading.
result Characterization of Nash equilibrium in a 1-period setting and initial insights into multi-period game.
In this work we afford the statistical characterization of a linear Stochastic Volatility Model featuring Inverse Gamma stationary distribution for the instantaneous volatility. We detail the derivation of the moments of the return distribution, revealing the role of the Inverse Gamma law in the emergence of fat tails,…
This work shows how transformers use multi-concept word semantics for efficient in-context learning.
problem Understanding the connection between transformer-based LLMs' multi-concept semantic representation and their innovative in-context learning abilities.
method A concept-based low-noise sparse coding prompt model, leveraging advanced techniques to analyze the exponential convergence of 0-1 loss over non-convex training dynamics.
result Transformers leverage multi-concept word semantics to enable powerful and excellent out-of-distribution in-context learning.
A distinctive property of human and animal intelligence is the ability to form abstractions by neglecting irrelevant information which allows to separate structure from noise. From an information theoretic point of view abstractions are desirable because they allow for very efficient information processing. In artifici…
There is emerging interest in performing regression between distributions. In contrast to prediction on single instances, these machine learning methods can be useful for population-based studies or on problems that are inherently statistical in nature. The recently proposed distribution regression network (DRN) has sh…
Low-rank training improves neural network training on edge devices with non-volatile memory.
problem Training neural networks on edge devices with non-volatile memory, especially in terms of write density and auxiliary memory.
method Low-rank training scheme to address write density and auxiliary memory limitations.
result The low-rank training technique outperforms standard SGD in accuracy and weight writes.
Transformers can approximate posterior predictive distributions through in-context learning.
problem Bayesian prediction tasks, especially beyond point predictions.
method Gradient descent algorithm targeting posterior predictive mean and variance, followed by nonlinear mappings.
result Transformers can implement algorithms to approximate posterior predictive distributions.
We develop a model to study the role of rationality in economics and biology. The model's agents differ continuously in their ability to make rational choices. The agents' objective is to ensure their individual survival over time or, equivalently, to maximize profits. In equilibrium, however, rational agents who maxim…
A recent trend in machine learning has been to enrich learned models with the ability to explain their own predictions. The emerging field of Explainable AI (XAI) has so far mainly focused on supervised learning, in particular, deep neural network classifiers. In many practical problems however, label information is no…
Most artificial intelligence models have limiting ability to solve new tasks faster, without forgetting previously acquired knowledge. The recently emerging paradigm of continual learning aims to solve this issue, in which the model learns various tasks in a sequential fashion. In this work, a novel approach for contin…
New IRT method identifies useful datasets for ML classifier evaluation.
problem Lack of standard evaluation strategy for ML benchmarks.
method Applied Item Response Theory (IRT) to OpenML-CC18 benchmark.
result Not all datasets are useful for evaluating classifiers.
We demystify attention patterns in multi-head softmax models for linear data.
problem Understanding the training dynamics and emergent patterns in multi-head softmax attention models.
method Extensive empirical experiments and rigorous theoretical analysis.
result Multi-head softmax attention models approximate a debiased gradient descent predictor, outperforming single-head attention and achieving near-Bayesian optimality.
Study shows neural ODEs generalize well on synthetic graphs but struggle with degree heterogeneity and clustering.
problem Understanding neural ODEs on complex networks, especially with varying graph sizes and structures.
method Synthetic data from five dynamical systems on graphs, using Barabási-Barzel form vector fields.
result Degree heterogeneity and dynamical system type are primary factors affecting neural ODEs' generalization.
The global financial crisis in 2007-2009 demonstrated that systemic risk can spread all over the world through a complex web of financial linkages, yet we still lack fundamental knowledge about the evolution of the financial web. In particular, interbank credit networks shape the core of the financial system, in which …
Panda predicts chaotic systems without retraining, showing emergent properties.
problem Predicting chaotic systems with small errors.
method Trained on a synthetic dataset of chaotic dynamical systems using evolutionary algorithms.
result Panda predicts unseen chaotic systems with zero-shot learning.
Paper develops an attention mechanism for long-term scientific impact prediction.
problem Predicting the long-term impact of scientific papers based on citation records.
method Develops an attention mechanism to predict long-term scientific impact.
result Emphasizing the limited attention can better stand on the shoulders of giants.
Improved noise estimation in latent neural SDEs enhances model accuracy.
problem Latent neural SDEs underestimate noise, limiting their stochastic dynamics modeling.
method Explicit additional noise regularization in the loss function.
result Model accurately captures diffusion component of stochastic time series data.
Robots learn to handle complex tasks creatively using DRL.
problem Robotic manipulation challenges and intelligence.
method Designing challenging manipulation tasks, applying DRL for robot training.
result Robots exhibit creative and non-intuitive problem-solving.
The paper examines efficient algorithms for linear regression over resource-limited networks.
problem Efficient communication in distributed learning over resource-limited networks.
method Developed algorithms for communication-efficient learning of linear regression tasks.
result The algorithms enable a tradeoff between communication and learning with theoretical performance guarantees.
Tailoring the presentation of information to the needs of individual students leads to massive gains in student outcomes~\cite{bloom19842}. This finding is likely due to the fact that different students learn differently, perhaps as a result of variation in ability, interest or other factors~\cite{schiefele1992interest…
Modern society heavily relies on strongly connected, socio-technical systems. As a result, distinct risks threatening the operation of individual systems can no longer be treated in isolation. Consequently, risk experts are actively seeking for ways to relax the risk independence assumption that undermines typical risk…
The equity risk premium puzzle is that the return on equities has far exceeded the average return on short-term risk-free debt and cannot be explained by conventional representative-agent consumption based equilibrium models. We review a few attempts done over the years to explain this anomaly: 1. Inclusion of highly u…