← back

Deep-ML

463 ML coding challenges · 17 categories · 0/463 read

Linear Algebra

⊣ #1 Matrix-Vector Dot Product
⊣ #2 Transpose of a Matrix
⊣ #3 Reshape Matrix
⊣ #4 Calculate Mean by Row or Column
⊣ #5 Scalar Multiplication of a Matrix
⊣ #6 Calculate Eigenvalues of a Matrix
⊣ #7 Matrix Transformation
⊣ #8 Calculate 2x2 Matrix Inverse
⊣ #9 Matrix times Matrix
⊣ #11 Solve Linear Equations using Jacobi Method
⊣ #12 Singular Value Decomposition (SVD) of 2x2 Matrix
⊣ #13 Determinant of a 4x4 Matrix using Laplace's Expansion
⊣ #27 Transformation Matrix from Basis B to C
⊣ #28 SVD of a 2x2 Matrix
⊣ #35 Convert Vector to Diagonal Matrix
⊣ #37 Calculate Correlation Matrix
⊣ #48 Implement Reduced Row Echelon Form (RREF) Function
⊣ #55 2D Translation Matrix Implementation
⊣ #57 Gauss-Seidel Method for Solving Linear Systems
⊣ #58 Gaussian Elimination for Solving Linear Systems
⊣ #63 Implement the Conjugate Gradient Method for Solving Linear Systems
⊣ #65 Implement Compressed Row Sparse Matrix (CSR) Format Conversion
⊣ #66 Implement Orthogonal Projection of a Vector onto a Line
⊣ #67 Implement Compressed Column Sparse Matrix Format (CSC)
⊣ #68 Find the column space of a matrix
⊣ #74 Create Composite Hypervector for a Dataset Row
⊣ #76 Calculate Cosine Similarity Between Vectors
⊣ #83 Dot Product Calculator
⊣ #84 Phi Transformation for Polynomial Features
⊣ #117 Compute Orthonormal Basis for 2D Vectors
⊣ #118 Compute the Cross Product of Two 3D Vectors
⊣ #119 Solve System of Linear Equations Using Cramer's Rule
⊣ #121 Vector Element-wise Sum
⊣ #195 Matrix Determinant & Trace
⊣ #201 QR Decomposition
⊣ #328 Vector Norms (L1/L2/Frobenius)
⊣ #329 Matrix Rank
⊣ #330 Compute the Null Space (Kernel) of a Matrix
⊣ #331 Check Linear Independence of Vectors
⊣ #332 Check if Matrix is Positive Definite
⊣ #333 LU Decomposition of a Square Matrix
⊣ #334 Cholesky Decomposition

Statistics

⊣ #10 Calculate Covariance Matrix
⊣ #78 Descriptive Statistics Calculator
⊣ #95 Calculate the Phi Coefficient
⊣ #120 Bhattacharyya Distance Between Two Distributions
⊣ #211 Two-Sample T-Test Implementation
⊣ #212 Confidence Interval for Population Mean
⊣ #213 Bayesian Inference for Beta-Binomial Model
⊣ #293 Calculate P50/P95/P99 Latency Percentiles
⊣ #296 Calculate Statistical Power for Experiment Design
⊣ #337 Maximum Likelihood Estimation for Gaussian Distribution
⊣ #339 Beta Distribution PDF and Statistics
⊣ #340 Exponential Distribution PDF and CDF
⊣ #342 Demonstrate Law of Large Numbers with Sampling

Probability

⊣ #79 Binomial Distribution Probability
⊣ #80 Normal Distribution PDF Calculator
⊣ #81 Poisson Distribution Probability Calculator
⊣ #132 Simulate Markov Chain Transitions
⊣ #136 Calculate KL Divergence Between Two Multivariate Gaussian Distributions
⊣ #168 Calculate Conditional Probability from Data
⊣ #176 Chi-square Probability Distribution
⊣ #179 Expected Value and Variance of an n-Sided Die
⊣ #180 Conditional Probability from Joint Distribution
⊣ #181 Sampling Distribution of the Mean
⊣ #182 Central Limit Theorem Simulation
⊣ #184 Empirical Probability Mass Function (PMF)
⊣ #206 Variational Inference: ELBO Computation
⊣ #243 Compute Covariance from Joint Probability Mass Function
⊣ #244 Compute Total Probability using Law of Total Probability
⊣ #245 Hypergeometric Distribution PMF
⊣ #246 Birthday Problem Probability
⊣ #247 Negative Binomial Distribution Probability
⊣ #336 Compute Posterior Probability using Bayes' Theorem

Calculus

⊣ #116 Derivative of a Polynomial
⊣ #127 Find Captain Redbeard's Hidden Treasure
⊣ #202 Jacobian Matrix Calculation
⊣ #214 Chain Rule for Composite Functions
⊣ #215 Partial Derivatives of Multivariable Functions
⊣ #219 Derivative of Softmax
⊣ #220 Derivative of Cross-Entropy Loss w.r.t. Logits
⊣ #221 Newton's Method for Optimization
⊣ #312 Quotient Rule for Derivatives

Machine Learning

⊣ #14 Linear Regression Using Normal Equation
⊣ #15 Linear Regression Using Gradient Descent
⊣ #16 Feature Scaling Implementation
⊣ #17 K-Means Clustering
⊣ #18 Implement K-Fold Cross-Validation
⊣ #19 Principal Component Analysis (PCA) Implementation
⊣ #20 Decision Tree Learning
⊣ #21 Pegasos Kernel SVM Implementation
⊣ #29 Random Shuffle of Dataset
⊣ #30 Batch Iterator for Dataset
⊣ #31 Divide Dataset Based on Feature Threshold
⊣ #32 Generate Sorted Polynomial Features
⊣ #33 Generate Random Subsets of a Dataset
⊣ #34 One-Hot Encoding of Nominal Values
⊣ #36 Calculate Accuracy Score
⊣ #38 Implement AdaBoost Fit Method
⊣ #43 Implement Ridge Regression Loss Function
⊣ #45 Linear Kernel Function
⊣ #46 Implement Precision Metric
⊣ #47 Implement Gradient Descent Variants with MSE Loss
⊣ #50 Implement Lasso Regression using ISTA
⊣ #52 Implement Recall Metric in Binary Classification
⊣ #61 Implement F-Score Calculation for Binary Classification
⊣ #64 Implement Gini Impurity Calculation for a Set of Classes
⊣ #69 Calculate R-squared for Regression Analysis
⊣ #71 Calculate Root Mean Square Error (RMSE)
⊣ #72 Calculate Jaccard Index for Binary Classification
⊣ #73 Calculate Dice Score for Classification
⊣ #75 Generate a Confusion Matrix for Binary Classification
⊣ #77 Calculate Performance Metrics for a Classification Model
⊣ #86 Detect Overfitting or Underfitting
⊣ #91 Calculate F1 Score from Predicted and True Labels
⊣ #92 Linear Regression - Power Grid Optimization
⊣ #93 Calculate Mean Absolute Error (MAE)
⊣ #104 Binary Classification with Logistic Regression
⊣ #105 Train Softmax Regression with Gradient Descent
⊣ #106 Train Logistic Regression with Gradient Descent
⊣ #108 Measure Disorder in Apple Colors
⊣ #109 Implement Layer Normalization for Sequence Data
⊣ #131 Implement Efficient Sparse Window Attention
⊣ #135 Implement Early Stopping Based on Validation Loss
⊣ #138 Find the Best Gini-Based Split for a Binary Decision Tree
⊣ #139 Elastic Net Regression via Gradient Descent
⊣ #140 Bernoulli Naive Bayes Classifier
⊣ #141 Shift and Scale Array to Target Range
⊣ #144 Apriori Frequent Itemset Mining
⊣ #152 Implementing ROUGE Score
⊣ #153 StepLR Learning Rate Scheduler
⊣ #154 ExponentialLR Learning Rate Scheduler
⊣ #155 CosineAnnealingLR Learning Rate Scheduler
⊣ #160 Mixed Precision Training
⊣ #173 Implement K-Nearest Neighbors
⊣ #186 Gaussian Process for Regression
⊣ #188 Gradient Checkpointing
⊣ #192 Implement the Huber Loss Function
⊣ #193 Compute Confusion Matrix with Normalization
⊣ #194 Implement Label Smoothing for Multi-Class Cross-Entropy
⊣ #198 Implement Weight Decay as L2 Regularization
⊣ #199 Early Stopping Based on Validation Loss Plateau
⊣ #254 Silhouette Score for Clustering Evaluation
⊣ #255 Implement Focal Loss for Imbalanced Classification
⊣ #256 Calculate Davies-Bouldin Index for Clustering Evaluation
⊣ #258 Calinski-Harabasz Index for Clustering Evaluation
⊣ #259 Implement DBSCAN Clustering Algorithm
⊣ #260 Calculate Expected Calibration Error (ECE)
⊣ #261 Gaussian Naive Bayes Classifier
⊣ #275 Implement Stratified Train-Test Split
⊣ #276 Implement ROC Curve Calculation
⊣ #277 Calculate AUC (Area Under ROC Curve)
⊣ #278 Implement Precision-Recall Curve
⊣ #279 Calculate Matthews Correlation Coefficient
⊣ #280 Implement RBF (Gaussian) Kernel Function
⊣ #281 Implement Polynomial Kernel Function
⊣ #282 Calculate SVM Margin Width
⊣ #283 Implement Hinge Loss for SVM
⊣ #284 Implement Entropy-based Split Selection
⊣ #285 Decision Tree Pruning with Cost-Complexity
⊣ #286 Implement Decision Tree for Regression
⊣ #288 Implement Grid Search
⊣ #300 Implement Volume Bars Sampling
⊣ #301 Implement Dollar Bars Sampling
⊣ #305 Implement Hard Voting Classifier
⊣ #306 Implement Soft Voting Classifier
⊣ #307 Implement Bagging Classifier from Scratch
⊣ #308 Gradient Direction and Magnitude
⊣ #309 Product Rule for Derivatives
⊣ #310 Taylor Series Approximation
⊣ #311 Classify Critical Points Using Hessian Eigenvalues
⊣ #313 Numerical Gradient Checking
⊣ #314 Lagrange Multipliers for Constrained Quadratic Optimization
⊣ #315 Elo Rating System for Model Comparison
⊣ #338 Maximum A Posteriori (MAP) Estimation for Bernoulli Parameter
⊣ #341 Gaussian Mixture Model with EM Algorithm
⊣ #343 Implement Random Forest Feature Importance
⊣ #344 Implement Gradient Boosting Regressor Step
⊣ #345 Implement Out-of-Bag Score Calculation
⊣ #346 Implement Stacking Classifier
⊣ #347 XGBoost Objective Function Calculation
⊣ #348 Domain Expert Model Fusion
⊣ #349 Implement Kernel PCA with RBF Kernel
⊣ #350 Calculate Explained Variance Ratio for PCA
⊣ #351 Implement LLE (Locally Linear Embedding)
⊣ #352 Implement t-SNE Gradient Calculation
⊣ #353 Reconstruction Error from PCA
⊣ #362 Implement K-Means++ Initialization
⊣ #363 Implement Mini-Batch K-Means
⊣ #364 Implement Hierarchical Clustering (Agglomerative)
⊣ #365 Implement Gaussian Mixture Model (GMM) E-step
⊣ #366 Implement Gaussian Mixture Model (GMM) M-step
⊣ #367 Implement Isolation Forest for Anomaly Detection
⊣ #368 Calculate BIC/AIC for Model Selection
⊣ #377 Linear Learning Rate Decay
⊣ #378 Temperature Sampling
⊣ #385 Beam Search Decoding
⊣ #392 Implement Cosine Annealing with Warm Restarts
⊣ #411 Compute TTFT ITL and TPS from a Token Timestamp Stream
⊣ #413 End-to-End Latency Decomposition
⊣ #429 Quantization Quality Check via Perplexity Delta
⊣ #430 Draft-Target Speculative Decoding Simulation
⊣ #432 N-gram Speculation Dictionary Construction and Lookup
⊣ #433 Speculative Decoding Acceptance Rate vs Temperature
⊣ #434 Prefix Cache Hit Rate Calculator
⊣ #436 KV Cache Tiered Offloading Simulator
⊣ #439 Expert Parallelism Token Routing and Communication Cost
⊣ #440 Disaggregated Prefill-Decode Serving Simulator
⊣ #443 Embedding Quantization Quality via Cosine Similarity
⊣ #444 ASR Real-Time Factor for Parallel Chunk Transcription
⊣ #445 TTS Concurrent Real-Time Stream Capacity
⊣ #449 Autoscaling Replica Simulator with SLA Tracking
⊣ #450 Cold Start Latency Budget Breakdown
⊣ #451 Break-Even Pay-Per-Token API vs Dedicated GPU
⊣ #452 Continuous Batching vs Static Batching Throughput Comparison

Deep Learning

⊣ #22 Sigmoid Activation Function Understanding
⊣ #23 Softmax Activation Function Implementation
⊣ #24 Single Neuron
⊣ #25 Single Neuron with Backpropagation
⊣ #26 Implementing Basic Autograd Operations
⊣ #39 Implementation of Log Softmax Function
⊣ #40 Implementing a Custom Dense Layer in Python
⊣ #41 Simple Convolutional 2D Layer
⊣ #42 Implement ReLU Activation Function
⊣ #44 Leaky ReLU Activation Function
⊣ #49 Implement Adam Optimization Algorithm
⊣ #53 Implement Self-Attention Mechanism
⊣ #54 Implementing a Simple RNN
⊣ #56 KL Divergence Between Two Normal Distributions
⊣ #59 Implement Long Short-Term Memory (LSTM) Network
⊣ #62 Implement a Simple RNN with Backpropagation Through Time (BPTT)
⊣ #85 Positional Encoding Calculator
⊣ #87 Adam Optimizer
⊣ #89 The Pattern Weaver's Code
⊣ #94 Implement Multi-Head Attention
⊣ #96 Implement the Hard Sigmoid Activation Function
⊣ #97 Implement the ELU Activation Function
⊣ #98 Implement the PReLU Activation Function
⊣ #99 Implement the Softplus Activation Function
⊣ #100 Implement the Softsign Activation Function
⊣ #102 Implement the Swish Activation Function
⊣ #103 Implement the SELU Activation Function
⊣ #107 Implement Masked Self-Attention
⊣ #113 Implement a Simple Residual Block with Shortcut Connection
⊣ #114 Implement Global Average Pooling
⊣ #115 Implement Batch Normalization for BCHW Input
⊣ #123 Calculate Computational Efficiency of MoE
⊣ #124 Implement the Noisy Top-K Gating Function
⊣ #125 Implement a Sparse Mixture of Experts Layer
⊣ #126 Implement Group Normalization
⊣ #128 Dynamic Tanh: Normalization-Free Transformer Activation
⊣ #130 Implement a Simple CNN Training Function with Backpropagation
⊣ #134 Compute Multi-class Cross-Entropy Loss
⊣ #137 Implement a Dense Block with 2D Convolutions
⊣ #143 Instance Normalization (IN) Implementation
⊣ #145 Adagrad Optimizer
⊣ #146 Momentum Optimizer
⊣ #147 GeLU Activation Function
⊣ #148 Adamax Optimizer
⊣ #149 Adadelta Optimizer
⊣ #150 Nesterov Accelerated Gradient Optimizer
⊣ #151 Dropout Layer
⊣ #156 Implement SwiGLU activation function
⊣ #172 Muon Optimizer Update with Newton-Schulz Iteration
⊣ #174 Train a Simple GAN on 1D Gaussian Data
⊣ #177 Implement MuonClip (qk-clip) for Stabilizing Attention
⊣ #178 Implement Position-wise Feed-Forward Block with Residual and Dropout
⊣ #189 Implement Local Response Normalization (LRN)
⊣ #190 Overlapping Max Pooling
⊣ #208 Flash Attention v1 - Forward Pass
⊣ #216 Thanksgiving Feast Predictor: Softmax for Dish Selection
⊣ #217 Derivatives of Activation Functions
⊣ #218 Compute the Hessian Matrix
⊣ #222 LoRA: Low-Rank Adaptation Forward Pass
⊣ #223 QLoRA: Quantized Low-Rank Adaptation Forward Pass
⊣ #227 Knowledge Distillation Loss
⊣ #229 Sparse MoE Top-K Routing
⊣ #230 3D CNN Forward Pass Implementation
⊣ #231 Temperature Decay Scheduler
⊣ #232 PTX Loss for Catastrophic Forgetting Prevention (RLHF)
⊣ #233 Inference Head Pruning for Transformers
⊣ #234 Block-wise FP8 Quantization
⊣ #235 Implement the SGTM Parameter Update Step
⊣ #236 Mean Ablation for Circuit Discovery
⊣ #262 Implement the Mish Activation Function
⊣ #263 Implement Binary Cross-Entropy Loss
⊣ #264 Implement the Tanh Activation Function
⊣ #265 Implement 2D Average Pooling
⊣ #266 Implement the Hardtanh Activation Function
⊣ #267 Implement Neural Memory Update with Surprise and Momentum
⊣ #268 Implement Relativistic Critic Rewards for Adversarial Reasoning
⊣ #271 Implement Gated Attention
⊣ #287 Implement GRU Cell
⊣ #289 Implement Xavier/Glorot Weight Initialization
⊣ #290 Implement He Weight Initialization
⊣ #291 Calculate Number of Parameters in Neural Network
⊣ #292 Implement Gradient Clipping by Value
⊣ #294 Implement INT8 Quantization
⊣ #298 Implement mHC Forward Pass
⊣ #302 Diffusion Reconstruction Loss
⊣ #303 Forward Diffusion Process
⊣ #304 Forward & Backward Diffusion Process
⊣ #327 Engram Context-Aware Gating
⊣ #335 Train a Paris-Style Decentralized Expert Model
⊣ #358 Implement Core MDN Residualization
⊣ #359 Distance Correlation for Measuring Metadata Dependence
⊣ #360 MDN with Label Collinearity Control
⊣ #369 Implement Xavier/Glorot Weight Initialization
⊣ #370 Implement He Weight Initialization for Neural Networks
⊣ #371 Calculate Number of Parameters in Neural Network
⊣ #372 Implement RMSNorm (Root Mean Square Layer Normalization)
⊣ #373 Implement the Square ReLU Activation Function
⊣ #374 Character-Level Tokenizer (stoi/itos/BOS)
⊣ #375 Learned Positional Embeddings
⊣ #376 KV Cache for Efficient Autoregressive Attention
⊣ #381 Rotary Positional Embeddings (RoPE)
⊣ #384 Contrastive Loss (InfoNCE / SimCLR-style)
⊣ #386 Spectral Normalization
⊣ #387 Triplet Margin Loss
⊣ #388 Sliding Window Attention
⊣ #389 Mixture of Experts Load Balancing Loss
⊣ #390 Implement Multiquery Attention (MQA)
⊣ #391 Implement Grouped Query Attention (GQA)
⊣ #393 Implement Variational Autoencoder (VAE) Loss (ELBO)
⊣ #394 Implement Speculative Decoding Verification
⊣ #395 DDPM Noise Schedule (Linear Beta Schedule)
⊣ #396 Implement DDPM Reverse Sampling Step
⊣ #397 Classifier-Free Guidance for Conditional Diffusion
⊣ #398 DDIM Deterministic Sampling Step
⊣ #399 Diffusion Model U-Net Time Embedding
⊣ #400 Noise Prediction Loss for Diffusion Training
⊣ #401 Exponential Moving Average (EMA) for Diffusion Model Weights
⊣ #402 Latent Diffusion Encoding and Decoding
⊣ #403 Diffusion Cosine Noise Schedule
⊣ #404 Implement Score Matching for Score-Based Diffusion
⊣ #405 Multi-Head Latent Attention (MLA)
⊣ #406 NoPE (No Positional Embedding) with iRoPE Attention
⊣ #407 QK-Norm (Query-Key Normalization)
⊣ #408 Pre-Norm vs Post-Norm Transformer Block
⊣ #409 MoE with Shared Expert Forward Pass
⊣ #426 Post-Training Quantization with Per-Channel Scale Factors
⊣ #427 FP4 Quantization with Microscaling (MXFP4)
⊣ #428 Number Format Precision Comparison (FP16 vs BF16 vs FP8 vs FP4)
⊣ #431 EAGLE-Style Draft Model from Hidden States
⊣ #435 KV Cache Memory Budget and Eviction Policy
⊣ #438 Tensor Parallelism All-Reduce Communication Cost
⊣ #442 VLM Visual Token Count from Image Resolution and Patch Size
⊣ #446 Video Generation Latent Space Memory Estimation
⊣ #447 Classifier-Free Guidance Skip Speedup Calculator
⊣ #448 Context Parallelism with Ring Attention for Video Models
⊣ #453 Implement Graph Convolution Network (GCN) Layer
⊣ #456 Multi-term Memory Patchification for Video
⊣ #457 Implement Attention Sink Detection
⊣ #458 Implement Sigmoid MoE Router with Bias Correction
⊣ #460 First Frame Anchor Noise Injection
⊣ #461 Guidance Attention Mask for Chunked Video
⊣ #462 UniPC Predictor-Corrector Step
⊣ #463 Unified History Injection for Autoregressive Video Diffusion

NLP

⊣ #51 Optimal String Alignment Distance
⊣ #60 Implement TF-IDF (Term Frequency-Inverse Document Frequency)
⊣ #88 GPT-2 Text Generation
⊣ #90 BM25 Ranking
⊣ #110 Evaluate Translation Quality with METEOR Score
⊣ #111 Compute Pointwise Mutual Information
⊣ #129 Calculate Unigram Probability from Corpus
⊣ #320 Calculate Perplexity for Language Models
⊣ #321 BLEU Score for Text Generation
⊣ #322 Bradley-Terry Model for Pairwise Rankings
⊣ #325 Exact Match Score with Normalization
⊣ #326 MMLU Letter-Matching Evaluation
⊣ #380 Byte Pair Encoding (BPE) Tokenizer

Computer Vision

⊣ #70 Calculate Image Brightness
⊣ #82 Grayscale Image Contrast Calculator
⊣ #185 Optical Flow EPE with Masks (OmniWorld-style metric)
⊣ #191 PCA Color Augmentation
⊣ #237 Convert RGB Image to Grayscale
⊣ #238 Flip an Image Horizontally or Vertically
⊣ #239 Apply Zero Padding to an Image
⊣ #240 Bilinear Image Resizing
⊣ #241 Sobel Edge Detection
⊣ #242 Non-Maximum Suppression for Object Detection
⊣ #454 Autoregressive Video Chunk FPS Calculator
⊣ #455 Historical Context Compression Ratio
⊣ #459 Frame-Aware Corrupt for Drift Simulation

Reinforcement Learning

⊣ #101 Implement the GRPO Objective Function
⊣ #122 Policy Gradient with REINFORCE
⊣ #133 Implement Q-Learning Algorithm for MDPs
⊣ #142 Gridworld Policy Evaluation
⊣ #157 Implement the Bellman Equation for Value Iteration
⊣ #158 Epsilon-Greedy Action Selection for n-Armed Bandit
⊣ #159 Incremental Mean for Online Reward Estimation
⊣ #161 Exponential Weighted Average of Rewards
⊣ #162 Upper Confidence Bound (UCB) Action Selection
⊣ #163 Gradient Bandit Action Selection
⊣ #164 Gambler's Problem: Value Iteration
⊣ #165 Compute Discounted Return
⊣ #166 Evaluate Expected Value in a Markov Decision Process
⊣ #167 Calculate the Discounted Return for a Given Trajectory
⊣ #175 Implement the SARSA Algorithm on policy
⊣ #207 Monte Carlo Tree Search
⊣ #209 GSPO: Group Sequence Policy Optimization
⊣ #210 Dr. GRPO: Complete Objective Function
⊣ #224 Group Relative Advantage for GRPO
⊣ #225 KL Divergence Estimator for GRPO
⊣ #226 Pass@k and Majority Voting Evaluation Metrics
⊣ #228 Budget-Constrained RL Loss
⊣ #257 Compute Temporal Difference Error
⊣ #272 First-Visit Monte Carlo Prediction
⊣ #273 n-Step TD Prediction
⊣ #274 TD(lambda) with Eligibility Traces
⊣ #361 Fine-Tune Model Weights with RLHF Policy Gradient
⊣ #379 RAFT: Iterative Reward-Ranked Fine-Tuning Loop

Data Preprocessing

⊣ #112 Min-Max Scaling of Feature Values
⊣ #354 Handle Missing Data with Imputation
⊣ #355 Outlier Detection and Removal Using IQR Method
⊣ #356 Label Encoding for Ordinal Variables
⊣ #357 Handle Imbalanced Data with SMOTE

Optimization

⊣ #169 Implement AdamW Optimizer Step
⊣ #170 Muon Optimizer Step with Matrix Preconditioning
⊣ #196 Warmup + Cosine Decay Schedule
⊣ #197 Gradient Clipping by Global Norm
⊣ #200 Implement RMSProp Optimizer

Information Theory

⊣ #203 Jensen-Shannon Divergence
⊣ #204 Mutual Information
⊣ #205 Entropy & Cross-Entropy

LLM

⊣ #316 MMLU Log-Probability Scoring
⊣ #317 Rubric-Based LLM Judge Evaluation
⊣ #318 Boxed Answer Extraction for Math Benchmarks
⊣ #319 Math Answer Verification with Equivalence Checking
⊣ #323 Pairwise Preference Judge for LLM Comparison
⊣ #324 Code Execution Verifier for Programming Benchmarks
⊣ #382 Direct Preference Optimization (DPO) Loss
⊣ #383 Top-p (Nucleus) Sampling
⊣ #410 Speculative Decoding End-to-End Simulation

Inference

⊣ #414 Compute Arithmetic Intensity and Classify Bottleneck
⊣ #415 Roofline Model Analysis for GPU Operations
⊣ #416 Compute Attention Memory Traffic and FLOPs
⊣ #417 Classify LLM Prefill vs Decode as Compute-Bound or Memory-Bound
⊣ #418 Estimate KV Cache Size from Model Config
⊣ #419 Combined Token Sampling Pipeline (Temperature + Top-k + Top-p)
⊣ #420 Latent Space Patchification for Diffusion Transformers
⊣ #421 GPU Ops:Byte Ratio Calculation from Spec Sheet
⊣ #422 Multi-GPU Communication Overhead (NVLink vs InfiniBand)
⊣ #423 Multi-Instance GPU (MIG) Resource Allocation
⊣ #424 Kernel Fusion Memory Savings Calculator
⊣ #425 Continuous Batching (In-Flight Batching) Simulator

MLOps

⊣ #187 Build a Simple ETL Pipeline (MLOps)
⊣ #248 Calculate Model Inference Statistics for Monitoring
⊣ #249 Calculate Batch Prediction Health Metrics
⊣ #250 Calculate SLA Compliance Metrics for Model Service
⊣ #251 Analyze Canary Deployment Health for Model Rollout
⊣ #252 Data Quality Scoring for ML Pipelines
⊣ #253 Feature Drift Detection using Population Stability Index
⊣ #269 A/B Test Statistical Analysis for Model Comparison
⊣ #270 ML Pipeline DAG Scheduler with Critical Path Analysis
⊣ #295 Implement Prediction Distribution Monitoring
⊣ #297 Implement Request Batching for Inference
⊣ #412 Estimate Minimum GPU Count for Model Deployment
⊣ #437 Cache-Aware Request Routing Across Replicas
⊣ #441 Chunked Prefill Scheduling Alongside Decode

Financial ML

⊣ #183 Calculate Portfolio Variance
⊣ #299 Implement Tick Bars Sampling

Game Theory

⊣ #171 Minimax Algorithm for Tic-Tac-Toe