Online Convex Optimization Using Predictions Niangjun Chen Joint
- Slides: 52
Online Convex Optimization Using Predictions Niangjun Chen Joint work with Anish Agarwal, Lachlan Andrew, Siddharth Barman, and Adam Wierman 1
2
3
online convex switching cost Goal: Algorithms to minimize cost 4
Lots of applications … Dynamic capacity management in data centers [Tu et al. 2013] Power system generation/load scheduling[Lu et al. 2013] Portfolio management [Cover 1991][Boyd et al. 2012] Video streaming [Sen et al. 2000][Liu et al. 2008] Network routing [Bansal et al. 2003][Kodialam et al. 2003] Geographical load balancing [Hindman et al. 2011] [Lin et al. 2012] … 5
In most applications, predictions are crucial But we do not have a good understanding about how (imperfect) predictions impact online algorithm design 6
This talk: Online Convex Optimization Using Predictions 7
8
9
10
Online convex optimization using predictions online convex switching cost Time Information Available Decision 1 … 2 … 3 … 4 … 11
How do algorithms model prediction noise? • Worst case analysis Average case analysis 12
Our contribution: a general and tractable model for prediction Key message: prediction allows 1. Overcoming “impossibility” results for OCO with minimal structural assumption 2. Mixture of average case and worst case analysis 13
Outline 1. Background : regret and competitive ratio OCO without prediction OCO with worst case prediction 2. Our prediction noise model 3. Algorithm design 4. OCO with stochastic prediction noise 14
Two communities, two metrics • Real applications want both 15
Guarantees without prediction ØSublinear regret? Yes, [Kivinen & Vempala 2002] [Bansal et al. 2003] [Zinkevich 2003] [Hazan et al. 2007] [Lin et al. 2012] … ØConstant CR? Yes, but only for scalar case [Blum et al. 1992] [Borodin et al. 1992][Blum & Burch 2000] [Lin et al. 2011][Lin et al. 2012] … ØSublinear regret and constant CR? Not even in scalar case! [Andrew et al. 2013] 16
Guarantees with prediction • Yes, [Kivinen & Vempala 2002] [Bansal et al. 2003] [Zinkevich 2003] [Hazan et al. 2007] [Lin et al. 2012] … Yes in general [Lin et al. 2013] Not without a lot of prediction [Chen et al. 2015] 17
We may be using the wrong prediction model 18
Outline 1. Background : regret and competitive ratio OCO without prediction OCO with worst case prediction 2. Our prediction noise model 3. Algorithm design 4. OCO with stochastic prediction noise 19
What do we want in a prediction noise model? Ø Predictions are “refined” as time goes forward Ø Predictions are more noisy as you look further ahead Ø Prediction errors can be correlated Ø Should be general enough to incorporate detailed models 20
A more realistic prediction noise model Realization that algorithm is trying to track prediction error 21
A more realistic prediction noise model Per-step noise How much uncertainty is there one step ahead? 22
A more realistic prediction noise model Weighting factor 23
A more realistic prediction noise model prediction error 24
A more realistic prediction noise model prediction error This form of prediction error matches what occurs in • Prediction of a wide-sense stationary process using a Weiner filter • Prediction of a linear dynamical system using a Kalman filter 25
A more realistic prediction noise model Allows adversarial analysis using stochastic prediction noise 26
Outline 1. Background : regret and competitive ratio OCO without prediction OCO with worst case prediction 2. Our prediction noise model 3. Algorithm design 4. OCO with stochastic prediction noise 27
A natural suggestion: Model Predictive Control (MPC) 28
A natural suggestion: Model Predictive Control (MPC) 29
A natural suggestion: Model Predictive Control (MPC) But MPC doesn’t work well in this setting … 30
A more stable alternative: Averaging Fixed Horizon Control (AFHC) Fixed Horizon Control (FHC) 31
A more stable alternative: Averaging Fixed Horizon Control (AFHC) Fixed Horizon Control (FHC) 32
A more stable alternative: Averaging Fixed Horizon Control (AFHC) … 33
Outline 1. Background : regret and competitive ratio OCO without prediction OCO with worst case prediction 2. Our prediction noise model 3. Algorithm design 4. OCO with stochastic prediction noise 34
35
How tight is this condition? 36
How to choose w? Loss due to switching Cumulative prediction error over w timesteps 37
How likely is large deviation from expected performance for AFHC? 38
Our contribution: a general and tractable model for prediction Key message: prediction allows 1. Overcoming “impossibility” results for OCO with minimal structural assumption AFHC can achieve sublinear regret and constant CR 2. Balance between average case and worst case analysis Concentration of AFHC around its mean performance 39
Online Convex Optimization Using Predictions Niangjun Chen Joint work with Anish Agarwal, Lachlan Andrew, Sid Barman, and Adam Wierman 40
Backup Slides 41
Predicting stationary process with Wiener Filter • 42
Predicting Linear Dynamical System Using Kalman Filter • 43
Proof Sketch 1. Within a lookahead window By perturbation analysis using Fenchel-Rockafellar duality Prediction error 44
Proof Sketch 2. Between lookahead windows cost between lookahead window 45
Proof Sketch … Average choices of FHC algorithms Switching cost Prediction error 46
Proof Sketch 4. Similarly for regret 47
Fixed Horizon Control Averaging Fixed Horizon Control 48
Online Convex Optimization Using Predictions online convex switching cost Goal: Algorithms to minimize cost Time Information Available Decision 1 … 2 … 3 … 49
Fixed Horizon Control Averaging Fixed Horizon Control 50
Online Convex Optimization Using Predictions online Time Information Available Decision 1 … 2 … 3 … 4 … Is there online algorithm that achieve sublinear regret and constant CR? Yes! 51
Averaging Fixed Horizon Control … Average choices of FHC algorithms 52
- Prediction error
- Convex polygon examples
- Convex hull is the smallest convex set
- Convex optimization in machine learning javatpoint
- Exact matrix completion via convex optimization
- Convex optimization
- Chen chen berlin
- Humeroulnar joint concave convex
- What is a peripheral joint
- How do you make predictions using experimental probability
- Making predictions with theoretical probability
- Joint optimization in family business
- Online optimization
- A grade lamb
- Ligamentum nuchae
- Examples of permanent joints
- Memorandum joint venture method
- Break joint vs spool joint
- Ellipsoid joint examples
- Jko joint knowledge online
- Will may might for predictions
- Names in romeo and juliet
- Making inferences and predictions
- Good readers make predictions by
- Making predictions powerpoint
- How to make a prediction on a scatter plot
- Assumptions generalizations predictions vs. conclusion
- Future simple predictions
- Reading comprehension making predictions
- Can you make predictions about tech devices
- Animal farm predictions
- Making predictions quiz
- Making predictions reading strategy
- Making predictions with probability
- Agatha predictions
- Click the arrow
- Predictions of progress reading recovery examples
- Tao lei
- It's your turn to make predictions
- Look at the following pictures and answer the questions
- Periosity
- Short. term. crypto. predictions.
- Barry smith predictions
- Intention prediction arrangement
- Fitness function in genetic algorithm
- Tsx blackberry
- Making predictions with probability
- First conditional predictions
- Names from romeo and juliet
- What are the limitations of punnett squares
- String theory predictions
- Polygon prediction
- Stresses