New method quantifies inductive bias for machine learning tasks.
problem Quantifying the amount of inductive bias in machine learning models.
method Estimates inductive bias by modeling loss distribution of random hypotheses.
result Higher dimensional tasks require greater inductive bias.
This research formalizes inductive generalization and proposes a new learning paradigm called Inductive Learning.
problem Generalization from easy to hard tasks, especially out-of-domain generalization.
method Formalizes inductive generalization, introduces Inductive Learning, and outlines steps to adapt techniques for learning model successors.
result A new learning paradigm (Inductive Learning) that emphasizes induction and universal properties of learning and computation.
Strong inductive biases prevent harmless interpolation in overparameterized models.
problem Understanding the conditions under which overparameterized models can interpolate noise without overfitting.
method Theoretical analysis of high-dimensional kernel regression and deep neural networks, focusing on the role of inductive biases.
result The strength of an estimator's inductive bias determines whether interpolation is harmless or requires fitting noise for good generalization.
I-BERT extends Transformer's self-attention to arbitrary input lengths.
problem Transformer models struggle with inductive generalization to unseen input lengths.
method Replaces positional encodings with a recurrent layer.
result I-BERT achieves state-of-the-art results on algorithmic tasks.
We introduce the notion of large scale inductive dimension for asymptotic resemblance spaces. We prove that the large scale inductive dimension and the asymptotic dimensiongrad are equal in the class of r-convex metric spaces. This class contains the class of all geodesic metric spaces and all finitely generated groups…
Study links neural network inductive bias, feature learning, and generalization on Boolean functions.
problem Understanding how neural networks learn and generalize on Boolean data.
method End-to-end analysis of depth-2 discrete fully connected networks and DNF formulas, using Monte Carlo learning.
result Predictable training dynamics and interpretable features emerge, linking inductive bias and generalization.
New approach relaxes inductive biases of physics-inspired NNs for better performance.
problem Challenges in applying physics-inspired NNs to real-world systems.
method Examined and relaxed inductive biases of Hamiltonian NNs, improving performance on non-conservative systems.
result Improved performance on practical, non-conservative systems by relaxing inductive biases.
Paper explores how knowledge distillation transfers inductive biases between models.
problem Transferring inductive biases between models for tasks with limited data.
method Knowledge distillation applied to models with different inductive biases (LSTMs vs. Transformers, CNNs vs. MLPs).
result Effect of inductive biases is transferred through knowledge distillation, impacting both performance and solution characteristics.
Interpolated-MLPs control inductive bias for better performance in low-compute tasks.
problem Low-compute performance gap between MLPs and CNNs.
method Introduced Interpolated MLP (I-MLP) approach to control inductive bias incrementally.
result Continuous logarithmic relationship between inductive bias and performance in low-compute tasks.
Integrates inductive biases into VAEs using intermediary latent variables.
problem Ineffective mechanisms for incorporating inductive biases into VAEs.
method InteL-VAEs use an intermediary latent space to control encoding, with a parametric function to enforce desired properties.
result InteL-VAEs lead to better generative models and representations.
Noise affects the effectiveness of interpolating models, especially those with strong inductive biases.
problem The impact of noise on interpolating models with strong inductive biases.
method Analyzing linear and classification models with sparse ground truths, proving fast rates for interpolators.
result Strong inductive biases can lead to faster but noisier interpolators, contrary to intuition.
Transformers learn to use induction heads or shortcuts based on data diversity.
problem How data diversity influences the behavior of transformers.
method Gradient-based training of a single-layer transformer on a minimal task.
result Data diversity steers transformers toward induction heads or shortcuts.
Novel approach trains LLMs for inductive reasoning using probabilistic programs.
problem Training LLMs for inductive reasoning with sparse, ambiguous data.
method Program-based Posterior Training (PPT) using probabilistic inference.
result Significant improvement in estimation accuracy and alignment with human judgments.
GraIL predicts relations by reasoning over subgraphs, outperforming embeddings.
problem Relation prediction in knowledge graphs using latent representations is limited.
method Graph neural network with inductive bias to learn entity-independent relational semantics.
result GraIL outperforms existing rule-induction baselines in the inductive setting.
One-layer transformers can't solve induction heads task efficiently.
problem Solving the induction heads task efficiently with one-layer transformers.
method Communication complexity argument showing exponential size requirement.
result No one-layer transformer can solve the induction heads task efficiently.
OTI extends OTP for inductive semi-supervised learning.
problem Inductive semi-supervised learning for out-of-sample data.
method Optimal transport-based approach extended to inductive tasks.
result OTI outperforms state-of-the-art methods in experiments.
Improved stability and generalization for blackbox learned optimizers.
problem Stability and generalization issues in blackbox learned optimizers.
method Investigation using dynamical systems, modifications to optimizer architecture and meta-training procedure.
result Improved stability and generalization of learned optimizers.
We propose an inductive matrix completion model without using side information. By factorizing the (rating) matrix into the product of low-dimensional latent embeddings of rows (users) and columns (items), a majority of existing matrix completion methods are transductive, since the learned embeddings cannot generalize …
Study reveals biases in gradient descent for GLNs, improving neural network performance.
problem Understanding and improving the inductive biases of deep neural networks.
method Derive infinite-time training limit of gated linear networks and generalize to other networks.
result Theoretical framework captures key inductive biases of ReLU networks.
Study shows different trajectory prediction models generalize better under OoD conditions.
problem Comparing trajectory prediction models' robustness across different datasets.
method Training models on Argoverse 2 and testing on Waymo Open Motion, and vice versa, with various augmentation strategies.
result Smallest model with highest inductive bias performs best in OoD generalization.
Transformers learn rich in-context dependencies efficiently.
problem Understanding how transformers learn long-range dependencies efficiently.
method Approximation and dynamics analysis of induction head mechanisms.
result Abrupt transition from lazy to rich mechanisms during training.
Deep ResNets favor low bottleneck rank with proper hyperparameters.
problem Understanding the inductive bias of deep neural networks.
method Computed minimum-norm weights of a deep linear ResNet.
result Deep nonlinear ResNets have an inductive bias towards minimizing bottleneck rank.
We apply Murasugi-Tristram inequality to real algebraic curves of odd degree on RP2 with a deep nest, i.e. a nest of the depth k−1 where 2k+1 is the degree. For such curves, the ingredients of the Murasugi-Tristram inequality can be computed (or estimated) inductively using the computations for iterated torus li…
We propose a Poisson-Lie analog of the symplectic induction procedure, using an appropriate Poisson generalization of the reduction of symplectic manifolds with symmetry. Having as basic tools the equivariant momentum maps of Poisson actions, the double group of a Poisson-Lie group and the reduction of Poisson manifold…
A new method for document network embedding interprets and generalizes well.
problem Lack of interpretability and generalization to new documents in existing methods.
method Introduces Topic-Word Attention (TWA) and Inductive Document Network Embedding (IDNE) to generate document representations.
result Achieves state-of-the-art performance on various networks and produces meaningful representations.
This research explores inductive biases for deep learning to improve AI's higher-level cognition.
problem Current AI struggles with flexible out-of-distribution and systematic generalization.
method Examines and proposes new inductive biases for deep learning.
result Identifies specific inductive biases for higher-level sequential processing.
We introduce several methods to define the self-inductance of a single loop as the regularization of divergent integrals which we obtain by applying Neumann (or Weber) formula for the mutual inductance of a pair of loops to the case when two loops are identical.
Proposes a topological framework to study modular invariants and related concepts.
problem Exploring modular invariants and related concepts in topological quantum field theory.
method Topological paradigm in alterfold topological quantum field theory.
result Establishes a novel integral identity for modular invariance across multiple Morita contexts.
New proof shows exotic 4-manifolds exist without complex calculations.
problem Existence of exotic 4-manifolds in topology.
method Used Beliakova and Wehrli's s-invariant for links in S3 and Stošić's induction scheme to simplify computations. result Existence of exotic compact, orientable 4-manifolds proven without skein lasagna modules.
Local nonparametric meta-learning improves meta-generalization across tasks.
problem Meta-learning struggles with global inductive biases and out-of-distribution tasks.
method Proposes a local, nonparametric meta-learning algorithm using meta-trained local learning rules.
result Improved meta-generalization and state-of-the-art results in robotics benchmarks.
If p:Y→X is an unramified covering map between two compact oriented surfaces of genus at least two, then it is proved that the embedding map, corresponding to p, from the Teichmüller space T(X), for X, to T(Y) actually extends to an embedding between the Thurston compactification of the tw…
Extract symbolic models from deep learning with inductive biases.
problem Interpreting and discovering physical principles from deep neural networks.
method Introduce strong inductive biases in GNNs, encourage sparse latent representations, apply symbolic regression.
result Extracted symbolic equations from neural networks, including known force laws and new analytic formulas.
Novel framework for Bayesian reinforcement learning infers value function distributions.
problem Bayesian reinforcement learning's challenges in inferring value function distributions.
method Inferential Induction framework for Bayesian reinforcement learning, developing Bayesian Backwards Induction algorithm.
result Proposed algorithm is competitive with state-of-the-art methods.
New diagnostic tool for assessing approximate Bayesian inference.
problem Assessing the trustworthiness of approximate Bayesian inference.
method Reframe the problem in terms of incompatible conditional distributions and use Gibbs priors.
result The diagnostic tool can discover the inductive bias in various Bayesian models and approximations.
Proposes a neural framework to select subsets efficiently across different models.
problem Lack of generalizability in subset selection methods for unseen architectures.
method Introduces a trainable subset selection framework, SubSelNet, that uses attention-based neural gadgets and subset samplers.
result SubSelNet generalizes across architectures and outperforms existing methods.
Unsupervised machine translation---i.e., not assuming any cross-lingual supervision signal, whether a dictionary, translations, or comparable corpora---seems impossible, but nevertheless, Lample et al. (2018) recently proposed a fully unsupervised machine translation (MT) model. The model relies heavily on an adversari…
IMM generates high-quality samples in few steps with stable training.
problem Slow inference and instability in generating high-quality samples using diffusion models and Flow Matching.
method Inductive Moment Matching (IMM) is a new generative model for one- or few-step sampling with a single-stage training procedure.
result IMM achieves state-of-the-art 2-step FID of 1.98 on CIFAR-10 for a model trained from scratch.
Low-dimensional embeddings of nodes in large graphs have proved extremely useful in a variety of prediction tasks, from content recommendation to identifying protein functions. However, most existing approaches require that all nodes in the graph are present during training of the embeddings; these previous approaches …
Node Masking improves GNNs' scalability and generalization.
problem Improving GNNs' ability to handle arbitrary graphs.
method Introducing Node Masking to enhance GNNs' performance.
result Node Masking enables GNNs to generalize and scale better.
Many deep reinforcement learning algorithms contain inductive biases that sculpt the agent's objective and its interface to the environment. These inductive biases can take many forms, including domain knowledge and pretuned hyper-parameters. In general, there is a trade-off between generality and performance when algo…
In high dimensional settings, density estimation algorithms rely crucially on their inductive bias. Despite recent empirical success, the inductive bias of deep generative models is not well understood. In this paper we propose a framework to systematically investigate bias and generalization in deep generative models …
VAEs improve generalization by regulating mutual information, contrary to intuition.
problem Improving generalization in VAEs.
method Rate-distortion analyses controlling rate strength, network capacity, and generalization difficulty.
result Decreasing the strength of the rate paradoxically improves generalization.
New method for embedding large networks without attributes, achieving state-of-the-art performance.
problem Learning embeddings from large-scale networks without domain-dependent attributes.
method Use predefined local encodings based on node degree frequencies at different distances.
result Inductive network embeddings generalize well across unseen or distant regions in the network.
We prove addition and subspace theorems for asymptotic large inductive dimension. We investigate a transfinite extension of this dimension and show that it is trivial.
Extends positive mass theorem to arbitrary dimensions using a new inductive scheme.
problem Overcoming singularities in the Schoen-Yau proof for arbitrary dimensions.
method Inductive scheme combining shielding principle, conformal blow-up, and Cheeger-Naber bound.
result Proof of positive mass theorem in arbitrary dimensions.
Ensemble method detects time series anomalies without preselecting parameter values.
problem Anomaly detection requires known anomaly length, limiting practicality.
method Ensemble grammar induction for variable-length anomalies.
result Ensemble approach outperforms existing methods with different parameter selections.
This work addresses encoding biases in neural networks by tailoring models with unsupervised losses.
problem Improving neural network representations and reducing the generalization gap.
method Inspired by transductive learning, the authors propose tailoring and meta-tailoring to optimize unsupervised losses during prediction time.
result Models trained with tailoring and meta-tailoring perform better on the task objective after adapting to unsupervised losses.
ISA learns subgoals for reinforcement learning agents.
problem Learning subgoals for efficient reinforcement learning.
method Induces a subgoal automaton from observation traces using inductive logic programming.
result ISA learns subgoals that improve RL performance and convergence.