🎓How I Study AIHISA
📖Read
📄Papers📰Blogs🎬Courses
💡Learn
🛤️Paths📚Topics💡Concepts🎴Shorts
🎯Practice
📝Daily Log🎯Prompts🧠Review
SearchSettings
How I Study AI - Learn AI Papers & Lectures the Easy Way

Concepts12

Groups

📐Linear Algebra15📈Calculus & Differentiation10🎯Optimization14🎲Probability Theory12📊Statistics for ML9📡Information Theory10🔺Convex Optimization7🔢Numerical Methods6🕸Graph Theory for Deep Learning6🔵Topology for ML5🌐Differential Geometry6∞Measure Theory & Functional Analysis6🎰Random Matrix Theory5🌊Fourier Analysis & Signal Processing9🎰Sampling & Monte Carlo Methods10🧠Deep Learning Theory12🛡️Regularization Theory11👁️Attention & Transformer Theory10🎨Generative Model Theory11🔮Representation Learning10🎮Reinforcement Learning Mathematics9🔄Variational Methods8📉Loss Functions & Objectives10⏱️Sequence & Temporal Models8💎Geometric Deep Learning8

Category

🔷All∑Math⚙️Algo🗂️DS📚Theory

Level

AllBeginnerIntermediate
📚TheoryIntermediate

Multi-Task Loss Balancing

Multi-task loss balancing aims to automatically set each task’s weight so that no single loss dominates training.

#multi-task learning#uncertainty weighting#homoscedastic uncertainty+12
📚TheoryAdvanced

In-Context Learning Theory

In-context learning (ICL) means a model learns from examples provided in the input itself, without updating its parameters.

#in-context learning
Advanced
Filtering by:
#gradient descent
#transformer
#attention
+12
📚TheoryIntermediate

Early Stopping

Early stopping halts training when the validation loss stops improving, preventing overfitting and saving compute.

#early stopping#validation loss#patience+11
📚TheoryAdvanced

Feature Learning vs Kernel Regime

The kernel (lazy) regime keeps neural network parameters close to their initialization, making training equivalent to kernel regression with a fixed kernel such as the Neural Tangent Kernel (NTK).

#neural tangent kernel#kernel ridge regression#lazy training+12
📚TheoryIntermediate

Implicit Bias of Gradient Descent

In underdetermined linear systems (more variables than equations), gradient descent started at zero converges to the minimum Euclidean norm solution without any explicit regularizer.

#implicit bias#gradient descent#minimum norm+12
📚TheoryIntermediate

Universal Approximation Theorems

The Universal Approximation Theorems say that a neural network with at least one hidden layer and a suitable activation can approximate any continuous function on a compact domain as closely as you like.

#universal approximation theorem#cybenko#hornik+12
📚TheoryIntermediate

Empirical Risk Minimization

Empirical Risk Minimization (ERM) chooses a model that minimizes the average loss on the training data.

#empirical risk minimization#expected risk#loss function+12
📚TheoryIntermediate

Loss Landscape Analysis

A loss landscape is the “terrain” of a model’s loss as you move through parameter space; valleys are good solutions and peaks are bad ones.

#loss landscape#sharpness#hessian eigenvalues+12
📚TheoryAdvanced

Calculus of Variations

Calculus of variations optimizes functionals—numbers produced by whole functions—rather than ordinary functions of numbers.

#calculus of variations#euler–lagrange#functional derivative+12
📚TheoryIntermediate

Convex Optimization

Convex optimization studies minimizing convex functions over convex sets, where every local minimum is guaranteed to be a global minimum.

#convex optimization#convex function#convex set+12
📚TheoryIntermediate

Optimization Theory

Optimization theory studies how to choose variables to minimize or maximize an objective while respecting constraints.

#optimization#convex optimization#gradient descent+12
📚TheoryIntermediate

Gradient Descent Convergence Theory

Gradient descent updates parameters by stepping opposite the gradient: x_{t+1} = x_t - \eta \nabla f(x_t).

#gradient descent#convergence rate#l-smooth+12